Lexical Semantics and Speech Understanding

• E. Briakou, N. Athanasiou, and A. Potamianos, "Cross-topic distributional semantic representations via unsupervised mappings," in Proc. Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers), (Minneapolis, MN), pp. 1052-1061, June 2019.

• G. Karamanolakis, E. Iosif, A. Zlatintsi, A. Pikrakis, and A. Potamianos, "Audio-based distributional semantic models for music auto-tagging and similarity measurement," in Proc of Multi-Learn Workshop at EUSIPCO, (Kos, Greece), Aug. 2017.

• G. Karamanolakis, E. Iosif, A. Zlatintsi, A. Pikrakis, and A. Potamianos, "Audio-based distributional representations of meaning using a fusion of feature encodings," in Proc. Interspeech, San Francisco, CA, Sept. 2016.

• E. Iosif and A. Potamianos, "Crossmodal network-based distributional semantic models," in Proc. Intl. Conf. on Language Resources and Evaluation, Portoroz, Slovenia, May 2016.

• E. Iosif, S. Georgiladakis, and A. Potamianos, "Cognitively motivated distributional representations of meaning," in Proc. Intl. Conf. on Language Resources and Evaluation, Portoroz, Slovenia, May 2016.

• S. Georgiladakis, E. Iosif, and A. Potamianos, "Fusion of compositional network-based and lexical function distributional semantic models," in Proc. Workshop on Cognitive Modeling and Computational Linguistics (CMCL), Denver, Colorado, pp. 39-47, June 2015.

• G. Athanasopoulou, I. Klasinas, S. Georgiladakis, E. Iosif, and A. Potamianos, " Using lexical, syntactic and semantic features for non-terminal grammar rule induction in spoken dialogue systems," in Proc. IEEE/ACM Workshop on Spoken Language Technology, Lake Tahoe, Nevada, Dec. 2014.

• G. Athanasopoulou, E. Iosif, and A. Potamianos, "Low-dimensional manifold distributional semantic models," in Proc. Intl. Conf. on Computational Linguistics, Dublin, Ireland, Aug. 2014.

• S. Georgiladakis, C. Unger, E. Iosif, S. Walter, P. Cimiano, E. Petrakis, and A. Potamianos, "Fusion of knowledge-based and data-driven approaches to grammar induction," in Proc. Interspeech, (Singapore), Sept. 2014.

• N. Malandrakis, M. Falcone, C. Vaz, J. J. Bisogni, A. Potamianos, and S. Narayanan, "Sail: Sentiment analysis using semantic similarity and contrast features," in Proc. Intl. Workshop on Semantic Evaluation, Dublin, Ireland, Aug. 2014.

• I. Klasinas, E. Iosif, K. Louka, and A. Potamianos, "Semeval-2014 task 2: Grammar induction for spoken dialogue systems," in Proc. Intl. Workshop on Semantic Evaluation, Dublin, Ireland, pp. 9-16, Aug. 2014.

• A. Chorianopoulou, G. Athanasopoulou, E. Iosif, I. Klasinas, and A. Potamianos, "tucsage: Grammar rule induction for spoken dialogue systems via probabilistic candidate selection," in Proc. Intl. Workshop on Semantic Evaluation, Dublin, Ireland, pp. 668-672, Aug. 2014.

• K. Zervanou, E. Iosif, and A. Potamianos, "Word semantic similarity for morphologically rich languages," in Proc. Intl. Conf. on Language Resources and Evaluation, Reykjavik, Iceland, pp. 1642-1648, May 2014.

• I. Klasinas, A. Potamianos, E. Iosif, S. Georgiladakis, and G. Mameli, "Web data harvesting for speech understanding grammar induction," in Proc. Interspeech, Lyon, France, Aug. 2013.

• E. Iosif and A. Potamianos, "Similarity computation using semantic networks created from web-harvested data," Natural Language Engineering, vol. FirstView, pp. 1-31, July 2013.

• T. Moschopoulos, E. Iosif, L. Demetropoulou, A. Potamianos, and S. Narayanan, "Toward the automatic extraction of policy networks using web links and documents," IEEE Transactions on Knowledge and Data Engineering, vol. 25, pp. 2404-2417, Oct. 2013.

• N. Malandrakis, A. Kazemzadeh, A. Potamianos, and S. S. Narayanan, "Sail: A hybrid approach to sentiment analysis," in Proc. 2nd Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), pp. 438-442, Association for Computational Linguistics, June 2013.

• E. Iosif, A. Potamianos, M. Giannoudaki, and K. Zervanou, "Semantic similarity computation for abstract and concrete nouns using network-based distributional semantic models," in Proc. 10th International Conference on Computational Semantics (IWCS), Potsdam, Germany, pp. 328-334, Mar. 2013.

• N. Malandrakis, E. Iosif, and A. Potamianos, "Deeppurple: Estimating sentence semantic similarity using n-gram regression models and web snippets," in *SEM 2012: The 1st Joint Conference on Lexical and Computational Semantics, Montreal, Canada, June 2012.

• N. Malandrakis, A. Potamianos, E. Iosif and S. Narayanan, "EmotiWord: Affective Lexicon Creation with Application to Interaction and Multimedia Data ,"in Proc. MUSCLE International Workshop on Computational Intelligence for Multimedia Understanding , Pisa, Italy, Dec. 2011.

• E. Iosif, and A. Potamianos, "Unsupervised Semantic Similarity Computation Between Terms Using Web Documents ,'' IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 11 , pp. 1637-1647, Nov. 2010.

• A. Tegos, V. Karkaletsis, and A. Potamianos, "Learning of Semantic Relations Between Ontology Concepts Using Statistical Techniques ", in Proc. HLIE Workshop , Antwerp, Belgium, Sept. 2008.

• E. Iosif and A. Potamianos, "Unsupervised semantic similarity computation using web search engines ,'' in Proc. Intern. Conf. on Web Intelligence, Silicon Valley, USA, Nov. 2007.

• E. Iosif and A. Potamianos, "A soft-clustering algorithm for automatic induction of semantic classes ,'' in Proc. Interspeech, Antwerp, Belgium, Aug. 2007.

• E. Ammicht, E. Fosler-Lussier, and A. Potamianos, "Information seeking spoken dialogue systems - Part I: Semantics and pragmatics ,'' IEEE Transactions on Multimedia, vol. 9, no.3, Apr. 2007. Vol. 9, pp. 532 - 549, April 2007.

• E. Iosif, A. Tegos, A. Pangos, E. Fosler-Lussier, and A. Potamianos, "Unsupervised combination of metrics for semantic class induction ,'' in IEEE/ACM Workshop on Spoken Language Technology, Aruba, Dec. 2006.

• A. Pangos, E. Iosif, A. Potamianos, and E. Fosler-Lussier, Combining statistical similarity measures for automatic induction of semantic classes ,'' in Proc. Automatic Speech Recogn. and Underst. Workshop, Cancun, Mexico, Dec. 2005.

• A. Pargellis, E. Fosler-Lussier, C.-H. Lee, A. Potamianos, and A. Tsai, "Auto-induced semantic classes,'' Speech Communication, vol. 43, pp. 183-203, Aug. 2004.

• A. Pargellis, E. Fosler-Lussier, A. Potamianos, and C.-H. Lee, "Metrics for measuring domain-independence of semantic classes ,'' in Proc. European Conf. on Speech Communication and Technology, Aalborg, Denmark, Oct. 2001.

• A. Potamianos and H.-K. Kuo, "Speech understanding using finite state transducers ,'' in Internat. Conf. Speech Language Processing, Beijing, China, Oct. 2000.

• A. Potamianos, G. Riccardi, and S. Narayanan, "Categorical understanding using statistical n-gram models,'' in Proc. European Conf. on Speech Communication and Technology, Budapest, Hungary, Sept. 1999.

• A. Potamianos and P. Maragos, "Time-frequency distributions for automatic speech recognition ,'' in Proc. Workshop on Automatic Speech Recognition and Understanding, Keystone, Colorado, Dec. 1999.

Robust Speech Recognition

• G. Paraskevopoulos, T. Kouzelis, G. Rouvalis, A. Katsamanis, V. Katsouros, and A. Potamianos, "Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems: A Case Study for Modern Greek," IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 32, pp. 286-299, Oct. 2023.

• A. Tsiartas, T. Chaspari, A. Katsamanis, P. Ghosh, M. Li, M. V. Segbroeck, A. Potamianos, and S. Narayanan, "Multi-band long-term signal variability features for robust voice activity detection," in Proc. Interspeech, Lyon, France, Aug. 2013.

• D. Dimitriadis, P. Maragos, and A. Potamianos, "On the Effects of Filterbank Design and Energy Computation on Robust Speech Recognition ," IEEE Transactions on Audio, Speech and Language Processing, vol. 19, no. 6, pp. 1504-1516, Aug. 2011.

• P. Tsiakoulis, A. Potamianos, and D. Dimitriadis, "Spectral Moment Features Augmented by Low Order Cepstral Coefficients for Robust ASR ," IEEE Signal Processing Letters, vol. 17, no. 6, pp. 551-554, June 2010.

• P. Tsiakoulis, A. Potamianos, and D. Dimitriadis, "Short-time instantaneous frequency and bandwidth features for speech recognition ," in Proc. Automatic Speech Recogn. and Underst. Workshop (ASRU), Merano, Italy, Dec. 2009.

• E. Sanchez-Soto, A. Potamianos, and K. Daoudi, "Unsupervised stream weight computation in classification and recognition tasks ,'' IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 3, pp. 436-445, Mar. 2009.

• S. Dimopoulos, A. Potamianos, E. Fosler-Lussier, and C.-H. Lee, "Multiple Time Resolution Analysis of Speech Signals Using MCE Training with Application to Speech Recognition ,"in Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, Apr. 2009.

• S. Dimopoulos, C.H. Lee, E. Fosler-Lussier, and A. Potamianos, "Transition features for CRF-based recognition and boundary detection ," in Proc. Automatic Speech Recogn. and Underst. Workshop (ASRU), Merano, Italy, Dec. 2009.

• M. Maragakis and A. Potamianos, "Region-Based Vocal Tract Length Normalization for ASR ", in Proc. Interspeech , Brisbane, Australia, Sept. 2008.

• E. Sanchez-Soto, K. Daoudi, and A. Potamianos, "Unsupervised stream weight computation in a segmentation task: Application to audio-visual speech recognition ,'' in Proc. Intern. Conf. on Signal Proc. and Communications, Dubai, UAE, Nov. 2007.

• D. Dimitriadis, J. Segura, L. Garcia, A. Potamianos, P. Maragos, and V. Pitsikalis, "Advanced front-end for robust speech recognition in extremely adverse environments ,'' in Proc. Interspeech, Antwerp, Belgium, Aug. 2007.

• E. Sanchez-Soto, A. Potamianos, and K. Daoudi, "Unsupervised stream weight computation using anti-models ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Hawaii, USA, Apr. 2007.

• A. Potamianos, E. Sanchez-Soto, and K. Daoudi, "Stream weight computation for multi-stream classifiers ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Toulouse, France, May 2006.

• A. Potamianos et al, "Towards speaker and enviromental robustness in ASR: the HIWIRE project ,'' in ITRW Workshop on Speech Recognition and Intrinsic Variation, Toulouse, France, May 2006.

• D. Dimitriadis, P. Maragos, and A. Potamianos, "Robust AM-FM features for speech recognition ,'' IEEE Signal Processing Letters, vol. 12, pp. 621-624, Sept. 2005.

• D. Dimitriadis, P. Maragos, and A. Potamianos, "Auditory Teager energy cepstrum coefficients for robust speech recognition ,'' in Proc. European Conf. on Speech Communication and Technology, Lisbon, Portugal, Sept. 2005.

• V. Weerackody, W. Reichl and A. Potamianos, "Soft feature decoding in a distributed automatic speech recognition system for use over wireless channels," U.S. Patent No. 6,760,699, awarded to Lucent Technologies, 2004.
• A. Potamianos and S. Narayanan, "Robust recognition of children's speech ,'' IEEE Transactions on Speech and Audio Processing, vol. 11, pp. 603-616, Nov. 2003.

• D. Dimitriadis, P. Maragos, and A. Potamianos, "Modulation features for speech recognition ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Orlando, Florida, May 2002.

• A. Potamianos, "Novel features for robust speech recognition,'' in invited presentation to the Conf. of the Acoustical Society of America, Cancun, Mexico, Dec. 2002.

• D. Dimitriadis, V. Pitsikalis, P. Maragos, and A. Potamianos, "Modulation and chaotic features for speech recognition ,'' invited paper to the Journal of Control and Intelligent Systems, Special Issue on Nonlinear Speech Processing, vol. 30, pp. 19-26, Jan. 2002.

• V. Weerackody, W. Reichl, and A. Potamianos, " An error-protected speech recognition system for wireless communications ,'' IEEE Transactions on Wireless Communications, vol. 1, pp. 282-291, Apr. 2002.

• A. Potamianos and P. Maragos, "Time-frequency distributions for automatic speech recognition ,'' IEEE Transactions on Speech and Audio Processing, vol. 9, pp. 196-200, Mar. 2001.

• A. Potamianos and V. Weerackody, "Soft-feature decoding for speech recognition over wireless channels ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Salt Lake City, Utah, May 2001.

• W. Reichl, V. Weerackody, and A. Potamianos, "A codec for speech recognition in a wireless system,'' in Proc. EUROCOMM, Munich, Germany, May 2000.

• I. Zeljkovic, S. Narayanan, and A. Potamianos, "Unsupervised HMM adaptation based on speech-silence discrimination," U.S. Patent No 6076057, awarded to AT&T, 2000.
• P.Maragos and A. Potamianos, "Fractal dimensions of speech sounds: Computation and application to automatic speech recognition ,'' Journal of the Acoustical Society of America, pp. 1925-1932, Mar. 1999.

• A. Potamianos and R. C. Rose, "Combining Frequency Warping And Spectral Shaping In HMM Based Speech Recognition," U.S. Patent No 5930753, awarded to AT&T, 1999.
• G. Potamianos and A. Potamianos, "Speaker adaptation for audio-visual speech recognition,'' in Proc. European Conf. on Speech Communication and Technology, Budapest, Hungary, Sept. 1999.

• S. Okawa, E. Brocchieri, and A. Potamianos, "Multi-band speech recognition in noisy environments ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Seattle, Washington, May 1998.

• P. Maragos and A. Potamianos, "On using fractal features of speech sounds in automatic speech recognition,'' in Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, pp. 2531-2534, Sept. 1997.

• A. Potamianos and R. C. Rose, "On combining frequency warping and spectral shaping in HMM-based speech recognition ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Munich, Germany, Apr. 1997.

• I. Zeljkovic, S. Narayanan, and A. Potamianos, "Unsupervised HMM adaptation based on speech-silence discrimination,'' in Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, pp. 2055-2058, Sept. 1997.

• R. C. Rose and A. Potamianos, "Improving robustness in HMM based speech recognition through simultaneous frequency warping and spectral shaping,'' in ESCA-NATO Workshop on Robust Speech Recognition, Pont-a-Mousson, France, Apr. 1997.

• A. Potamianos and R. C. Rose, "A feature-space transformation for telephone based speech recognition,'' in Proc. European Conf. on Speech Communication and Technology, Madrid, Spain, Sept. 1995.

• A. Potamianos and R. C. Rose, "A Time-Varying Feature Space Preprocessing Procedure for Telephone Based Speech Recognition," U.S. Patent No 5765124, awarded to Lucent Technologies, 1995.

Multimodal Dialogue Systems

• Y. Jo, X. Zhao, A. Biswas, N. Basiou, V. Auvray, N. Malandrakis, A. Metallinou, and A. Potamianos, "Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users,"in Findings of the Association for Computational Linguistics: EMNLP, (Singapore), pp. 3237-3269, Oct. 2023.

• S. Surya, Y. Jo, A. Biswas, and A. Potamianos, "A Zero-Shot Approach for Multi-User Task-Oriented Dialog Generation,"in Proc. of the International Natural Language Generation Conference, (Prague, Czechia), pp. 196-205, Sept. 2023.

• E. Kapelonis, E. Georgiou, and A. Potamianos, "A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking,"in Proc. Interspeech, (Incheon, Korea), pp. 2733-2737, Sept. 2022.

• E. Iosif, I. Klasinas, G. Athanasopoulou, E. Palogiannidi, S. Georgiladakis, K. Louka, and A. Potamianos, "Speech understanding for spoken dialogue systems: From corpus harvesting to grammar rule induction," Computer Speech and Language, vol. 47, pp. 272-297, Jan. 2018.

• P. Papalampidi, E. Iosif, and A. Potamianos, "Dialogue act semantic representation and classification using recurrent neural networks," in Proc. Workshop on the Semantics and Pragmatics of Dialogue, (Saabrucken, Germany), pp. 77-86, Aug. 2017.

• J. Lopes, A. Chorianopoulou, E. Palogiannidi, H. Moniz, A. Abad, K. Louka, E. Iosif, and A. Potamianos, "The Spedial datasets: datasets for spoken dialogue system analytics," in Proc. Intl. Conf. on Language Resources and Evaluation, Portoroz, Slovenia, May 2016.

• S. Georgiladakis, G. Athanasopoulou, R. Meena, J. Lopes, A. Chorianopoulou, E. Palogiannidi, E. Iosif, G. Skantze, and A. Potamianos, "Root cause analysis of miscommunication hotspots in spoken dialogue systems," in Proc. Interspeech, San Francisco, CA, Sept. 2016.

• E. Palogiannidi, I. Klasinas, A. Potamianos, and E. Iosif, "Spoken dialogue grammar induction from crowdsourced data," in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Florence, Italy, May 2014.

• G. Riccardi, P. Cimiano, A. Potamianos, and C. Unger, "Up from limited dialog systems!," in Proc. NAACL-HLT Workshop on future directions and needs in the SDS community (position paper), Montreal, Canada, June 2012.

• T. Kannetis, and A. Potamianos, "Towards Adapting Fantasy, Curiosity and Challenge in Multimodal Dialogue Systems for Preschoolers ,"in Proc. Int'l Conf. on Multimodal Interfaces (ICMI), Boston, MA, Nov. 2009.

• A. Potamianos and M. Perakakis, "Design Principles for Multimodal Spoken Dialogue Systems,'' in Multimodal Processing and Interaction: Audio, Video, Text, Springer-Verlag, 2008.

• M. Perakakis and A. Potamianos, "A study in efficiency and modality usage in multimodal form filling systems ,'' IEEE Transactions on Audio, Speech and Language Processing, Vol. 16, pp. 1194 - 1206, Aug. 2008.

• M. Perakakis and A. Potamianos, "Multimodal System Evaluation using Modality Efficiency and Synergy Metrics ", in Proc. Int'l Conf. on Multimodal Interfaces (ICMI), Chania, Greece, Oct. 2008.

• M. Perakakis and A. Potamianos, "The effect of input mode on inactivity and interaction times of multimodal systems ,'' in Internat. Conf. on Multimodal Interfaces, Nagoya, Japan, Nov. 2007.

• M. Perakakis, M. Toutoudakis, and A. Potamianos, "Blending speech and visual input in multimodal dialogue systems ,'' in IEEE/ACM Workshop on Spoken Language Technology, Aruba, Dec. 2006.

• A. Potamianos, S. Narayanan, and G. Riccardi, "Adaptive categorical understanding for spoken dialogue systems ,'' IEEE Transactions on Speech and Audio Processing, Vol. 13, pp. 321 - 329, May 2005.

• A. Potamianos, E. Ammicht, and E. Fosler-Lussier, "Modality tracking in the multimodal Bell Labs Communicator ,'' in Proc. Automatic Speech Recogn. and Underst. Workshop, St. Thomas, U.S. Virgin Islands, Dec. 2003.

• M. Tsangaris and A. Potamianos, "AGORA: A GUI approach to multimodal user interfaces ,'' in Proc. Human Language Technology Conf., San Diego, California, Mar. 2002.

• S. Lee, E. Ammicht, E. Fosler-Lussier, J. Kuo, and A. Potamianos, "Spoken dialogue evaluation for the Bell Labs Communicator system ,'' in Proc. Human Language Technology Conf., San Diego, California, Mar. 2002.

• R. Argiles-Solsona, E. Fosler-Lussier, J. Kuo, A. Potamianos, and I. Zitouni, "Adaptive language models for spoken dialogue systems ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Orlando, Florida, May 2002.

• M. Galley, E. Fosler-Lussier, and A. Potamianos, "Hybrid natural language generation for spoken dialogue systems ,'' in Proc. European Conf. on Speech Communication and Technology, Aalborg, Denmark, Oct. 2001.

• M. Walker et al, "DARPA Communicator: Cross-system results for the 2001 evaluation ,'' in Internat. Conf. Speech Language Processing, Colorado, Sept. 2002.

• E. Ammicht, A. Potamianos, and E. Fosler-Lussier, "Ambiguity representation and resolution in spoken dialogue systems ,'' in Proc. European Conf. on Speech Communication and Technology, Aalborg, Denmark, Oct. 2001.

• A. Potamianos, E. Ammicht, and H.-K. Kuo, "Dialogue management in the Bell Labs communicator system ,'' in Internat. Conf. Speech Language Processing, Beijing, China, Oct. 2000.

• M. Walker et al, "DARPA Communicator dialog travel planning systems: the June 2000 evaluation,'' in Proc. European Conf. on Speech Communication and Technology, Aalborg, Denmark, Oct. 2001.

• M. Walker et al, "DARPA Communicator evaluation: Progress from 2000 to 2001,'' in Internat. Conf. Speech Language Processing, Colorado, Sept. 2002.

• A. Potamianos et al, "Design principles and tools for multimodal dialog systems ,'' in Proc. ESCA Workshop Interact. Dialog. Multi-Modal Syst., Kloster Irsee, Germany, June 1999.

• G. Riccardi, A. Potamianos, and S. Narayanan, "Language model adaptation for spoken dialog systems ,'' in Internat. Conf. Speech Language Processing, Australia, Oct. 1998.

AM-FM Speech Model and Energy Operators

• P. Tsiakoulis, A. Potamianos, and D. Dimitriadis, "Instantaneous frequency and bandwidth estimation using filterbank arrays," in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Vancouver, Canada, May 2013.

• P. Tsiakoulis, and A. Potamianos, "On the Effect of Fundamental Frequency on Amplitude and Frequency Modulation Patterns in Speech Resonances,"in Proc. Interspeech , Makuhari, Japan, Sept. 2010.

• P. Tsiakoulis, and A. Potamianos, "Statistical Analysis of Amplitude Modulation in Speech Signals using an AM-FM Model ," in Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, Apr. 2009.

• D. Dimitriadis, A. Potamianos, and P. Maragos, "A Comparison of the Squared Energy and Teager-Kaiser Operators for Short-Time Energy Estimation in Noise ,'' IEEE Transactions on Signal Processing , vol. 57, no. 7, pp. 2569-2581, July 2009.

• A. Potamianos and P. Maragos, "Speech analysis and synthesis using an AM-FM modulation model ,'' Speech Communication, vol. 28, pp. 195-209, July 1999.

• A. Potamianos and P. Maragos, "Speech analysis and synthesis using an AM-FM modulation model,'' in Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, pp. 1355-1358, Sept. 1997.

• A. Potamianos, Speech Processing Applications Using an AM-FM Modulation Model, Harvard University, 1996

• A. Potamianos and P. Maragos, "Speech formant frequency and bandwidth tracking using multiband energy demodulation ,'' Journal of the Acoustical Society of America, vol. 99, pp. 3795-3806, June 1996.

• P. Maragos and A. Potamianos, "Higher-order differential energy operators ,'' IEEE Signal Processing Letters, vol. 2, Aug. 1995.

• P. Maragos, A. Potamianos, and B. Santhanam, "Instantaneous energy operators: Applications to speech processing and communications ,'' in IEEE Workshop on Nonlinear Signal and Image Processing, Thessaloniki, Greece, June 1995.

• A. Potamianos and P. Maragos, "Speech formant frequency and bandwidth tracking using multiband energy demodulation ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Detroit, MI, May 1995.

• A. Potamianos and P. Maragos, "Applications of speech processing using an AM-FM modulation model and energy operators ,'' in Proc. European Signal Process. Conf., Edinburgh, Scotland, pp. III: 1669-1672, Sept. 1994.

• P. Maragos, T. F. Quatieri, J. F. Kaiser, and A. Potamianos, "Demodulation of AM-FM resonances in speech using energy separation,'' in presentation to the Conf. of the Acoustical Society of America, Boston, MA, June 1994.

• A. Potamianos and P. Maragos, "A comparison of the energy operator and the Hilbert transform approach to signal and speech demodulation ,'' Signal Processing, vol. 37, pp. 95-120, May 1994.

• H. M. Hanson, P. Maragos, and A. Potamianos, "A system for finding speech formants and modulations via energy separation ,'' IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 436-443, July 1994.

• H. M. Hanson, P. Maragos, and A. Potamianos, "Finding speech formants and modulations via energy separation: With application to a vocoder,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Minneapolis, MN, Apr. 1993.

Children Speech Analysis, ASR and HCI

• A. Chorianopoulou, E. Tzinis, E. Iosif, A. Papoulidi, C. Papailiou, and A. Potamianos, "Engagement detection for children with autism spectrum disorder," in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., New Orleans, LA, pp. 5055-5059, Mar. 2017.

• S. Lee, A. Potamianos, and S. Narayanan, "Developmental acoustic study of American English diphthongs ,'' Journal of the Acoustical Society of America, vol. 136, pp. 1880-1894, Oct. 2014.

• D. Bone, C.-C. Lee, A. Potamianos, and S. Narayanan, "An investigation of vocal arousal dynamics in child-psychologist interactions using synchrony measures and a conversation-based model," in Proc. Interspeech, (Singapore), Sept. 2014.

• P. G. Shivakumar, A. Potamianos, S. Lee, and S. Narayanan, "Improving speech recognition for children using acoustic adaptation and pronunciation modeling," in Proc. Workshop on Child, Computer and Interaction, (Singapore), Sept. 2014.

• G. Evgeneiadis, V. Kouloumenta, and A. Potamianos, "Analyzing exploration and exploitation patterns in multimodal dialogue games for preschoolers," in Proc. Games for Learning Workshop - Foundations of Digital Games Conference, Chania, Greece, May 2013.

• V. Kouloumenta, M. Perakakis, and A. Potamianos, "Affective evaluation of multimodal dialogue games for preschoolers using physiological signals," in Proc. Interspeech, Lyon, France, Aug. 2013.

• M. Poesio, M. Baroni, O. Lanz, A. Lenci, A. Potamianos, H. Schutze, S. Schulte im Walde, and L. Surian, "BabyExp: Constructing a huge multimodal resource to acquire commonsense knowledge like children do,"in Proc. LREC , Malta, May. 2010.

• M. Gerosa, D. Giuliani, S. Narayanan, and A. Potamianos, "A Review of ASR Technologies for Children's Speech ," in Proc. Workshop of Child, Computer and Interaction (WOCCI), Boston, MA, Nov. 2009.

• T. Kannetis, A. Potamianos, and G.N. Yannakakis, "Fantasy, Curiosity and Challenge as Adaptation Indicators in Multimodal Dialog Systems for Preschoolers ," in Proc. Workshop of Child, Computer and Interaction (WOCCI), Boston, MA, Nov. 2009.

• V. Farantouri, A. Potamianos, and S. Narayanan, "Linguistic Analysis of Spontaneous Children Speech ", in Proc. Workshop of Child, Computer and Interaction (WOCCI), Chania, Greece, Oct. 2008.

• A. Potamianos and S. Narayanan, "A review of the acoustic and linguistic properties of children's speech ,'' in Proc. Intern. Workshop on Multimedia Signal Processing, Chania, Greece, Oct. 2007.

• S. Narayanan and A. Potamianos, "Creating conversational interfaces for children ,'' IEEE Transactions on Speech and Audio Processing, vol. 10, pp. 65-78, Feb. 2002. [IEEE Signal Processing Society Best Paper Award 2005]

• S. Narayanan, A. Potamianos, and H. Wang, "Multimodal systems for children: Building a prototype,'' in Proc. European Conf. on Speech Communication and Technology, Budapest, Hungary, Sept. 1999.

• S. Lee, A. Potamianos, and S. Narayanan, "Acoustics of children's speech: Developmental changes of temporal and spectral parameters ,'' Journal of the Acoustical Society of America, pp. 1455-1468, Mar. 1999. [Selected Research Article by JASA]

• A. Potamianos and S. Narayanan, "Spoken dialog systems for children ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Seattle,Washington, pp. 197-201, May 1998.

• S. Lee, A. Potamianos, and S. Narayanan, "Analysis of children's speech: Duration, pitch and formants,'' in Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, pp. 473-476, Sept. 1997.

• A. Potamianos, S. Narayanan, and S. Lee, "Automatic speech recognition for children,'' in Proc. European Conf. on Speech Communication and Technology, Rhodes, Greece, pp. 2371-2374, Sept. 1997.

Emotion Recognition and Behavioral Tracking

• E. Georgiou, Y. Avrithis, and A. Potamianos, "PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis," IEEE/ACM Transactions on Audio, Speech and Language Processing, submitted Dec. 2023.

• O. S. Chlapanis, G. Paraskevopoulos, and A. Potamianos, "Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis,"in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., (Singapore), Apr. 2023.

• I. Triantafyllopoulos, G. Paraskevopoulos, and A. Potamianos, "Depression detection in social media posts using affective and social norm features,"in arXiv preprint arXiv:2303.14279, Mar. 2023.

• G. Paraskevopoulos, E. Georgiou, and A. Potamianos, "Mmlatch: Bottom-up top-down fusion for multimodal sentiment analysis,"in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., (Singapore), May 2022.

• E. Georgiou, G. Paraskevopoulos, and A. Potamianos, "M3: Multimodal masking applied to sentiment analysis,"in Proc. Interspeech, (Brno, Czech Republic), pp. 2876-2880, Sept. 2021.

• E. Zaranis, G. Paraskevopoulos, A. Katsamanis, and A. Potamianos, "Empbot: A T5-based empathetic chatbot focusing on sentiments,"in arXiv preprint arXiv:2111.00310, Oct. 2021.

• A. Katsamanis, S. Narayanan, and A. Potamianos, "Deep actionable behavioral profiling and shaping," US Patent App. 16/441,521, 2019.
• G. Paraskevopoulos, E. Tzinis, N. Ellinas, T. Giannakopoulos, and A. Potamianos, "Unsupervised low-rank representations for speech emotion recognition," in Proc. Interspeech, Graz, Austria, pp. 939-943, Sept. 2019.

• T. Giannakopoulos, S. Dimopoulos, G. Pantazopoulos, A. Chatziagapi, D. Sgouropoulos, A. Katsamanis, A. Potamianos, and S. Narayanan, "Using oliver API for emotion-aware movie content characterization," in Proc. International Conference on Content-Based Multimedia Indexing (CBMI), Dublin, Ireland, pp. 1-4, Sept. 2019.

• A. Fergadis, C. Baziotis, D. Pappas, H. Papageorgiou, and A. Potamianos, "Hierarchical bi-directional attention-based RNNs for supporting document classification on protein-protein interactions affected by genetic mutations," Database, vol. 2018-1, pp. 1-10, Jan. 2018.

• C. Baziotis, N. Athanasiou, G. Paraskevopoulos, N. Ellinas, A. Kolovou, and A. Potamianos, "NTUA-SLP at SemEval-2018 Task 2: Predicting emojis using RNNs with context-aware attention," in Proc. Intl. Workshop on Semantic Evaluation, New Orleans, Louisiana, pp. 438-444, June 2018.

• E. Tzinis, G. Paraskevopoulos, C. Baziotis, and A. Potamianos, "Integrating recurrence dynamics for speech emotion recognition," in Proc. Interspeech, Hyderabad, India, pp. 927-931, Sept. 2018.

• F. Christopoulou, E. Briakou, E. Iosif, and A. Potamianos, "Mixture of topic-based distributional semantic and affective models," in Proc. IEEE Intl. Conf. on Semantic Computing, Laguna Hills, CA, pp. 203-210, Jan. 2018.

• A. Chronopoulou, A. Margatina, C. Baziotis, and A. Potamianos, "NTUA-SLP at IEST 2018: Ensemble of neural transfer methods for implicit emotion classification," in Proc. Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Brussels, Belgium, July 2018.

• E. Tzinis, G. Paraskevopoulos, C. Baziotis, and A. Potamianos, "Integrating recurrence dynamics for speech emotion recognition," in Proc. Interspeech, Hyderabad, India, pp. 927-931, Sept. 2018.

• C. Baziotis, N. Athanasiou, P. Papalampidi, A. Kolovou, G. Paraskevopoulos, N. Ellinas, and A. Potamianos, "NTUA-SLP at SemEval-2018 Task 3: Tracking ironic tweets using ensembles of word and character level attentive RNNs," in Proc. Intl. Workshop on Semantic Evaluation, (New Orleans, Louisiana), pp. 613-621, June 2018.

• A. Kolovou, E. Iosif, and A. Potamianos, "Lexical and affective models in early acquisition of semantics," in Proc. Workshop on Child Computer Interaction, Glasgow, Scotland, Nov. 2017.

• E. Tzinis and A. Potamianos, "Segment-based speech emotion recognition using recurrent neural networks," in Proc. of Intl. Conf. on Affective Computing and Intelligent Interaction, San Antonio, Texas, pp. 190-195, Oct. 2017.

• A. Zlatintsi, P. Koutras, G. Evangelopoulos, N. Malandrakis, N. Efthymiou, K. Pastra, A. Potamianos, and P. Maragos, "COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization," EURASIP Journal on Image and Video Processing, vol. 2017, p. 54, Jan. 2017.

• A. Kolovou, F. Kokkinos, A. Fergadis, P. Papalampidi, E. Iosif, N. Malandrakis, E. Palogiannidi, H. Papageorgiou, S. Narayanan, and A. Potamianos, "Tweester at SemEval-2017 Task 4: Fusion of semantic-affective and pairwise classification models for sentiment analysis in twitter," in Proc. Intl. Workshop on Semantic Evaluation, Vancouver, Canada, pp. 675-682, Aug. 2017.

• E. Palogiannidi, A. Kolovou, F. Christopoulou, F. Kokkinos, E. Iosif, N. Malandrakis, H. Papageorgiou, S. Narayanan, and A. Potamianos, "Tweester at semeval-2016 task 4: Sentiment analysis in twitter using semantic-affective model adaptation," in Proc. Intl. Workshop on Semantic Evaluation, San Diego, CA, June 2016.

• E. Palogiannidi, P. Koutsakis, E. Iosif, and A. Potamianos, "Affective lexicon creation for the Greek language," in Proc. Intl. Conf. on Language Resources and Evaluation, Portoroz, Slovenia, May 2016.

• A. Chorianopoulou, P. Koutsakis, and A. Potamianos, "Speech emotion recognition using affective saliency," in Proc. Interspeech, (San Francisco, CA), Sept. 2016.

• E. Palogiannidi, E. Iosif, P. Koutsakis, and A. Potamianos, "A semantic-affective compositional approach for the affective labelling of adjective-noun and noun-noun pairs," in Proc. of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA), San Diego, CA, June 2016.

• E. Iosif and A. Potamianos, "Feeling is understanding: From affective to semantic spaces," in Proc. Intl Conference for Computational Semantics (IWCS), London, UK, pp. 162-173, Apr. 2015.

• A. Vinciarelli, A. Esposito, E. Andre, F. Bonin, M. Chetouani, J. Cohn, M. Cristani, F. Fuhrmann, E. Gilmartin, Z. Hammal, D. Heylen, R. Kaiser, M. Koutsombogera, A. Potamianos, S. Renals, G. Riccardi, and A. Salah, "Open challenges in modelling, analysis and synthesis of human behaviour in human-human and human-machine interactions," Cognitive Computation, vol. 7, pp. 397-413, Apr. 2015.

• E. Palogiannidi, E. Iosif, P. Koutsakis, and A. Potamianos, "Valence, arousal and dominance estimation for english, german, greek, portuguese and spanish lexica using semantic models," in Proc. Interspeech, (Dresden, Germany), Sept. 2015.

• A. Potamianos, "Cognitive multimodal processing: from signal to behavior," in Proc. Workshop on Roadmapping the Future of Multimodal Interaction Research, Istanbul, Turkey, Nov. 2014.

• N. Malandrakis, A. Potamianos, K. J. Hsu, K. N. Babeva, M. C. Feng, G. C. Davison, and S. Narayanan, "Affective language model adaptation via corpus selection," in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Florence, Italy, May 2014.

• M. V. Segbroeck, R. Travadi, C. Vaz, J. Kim, M. Black, A. Potamianos, and S. Narayanan, "Classification of cognitive load from speech using an i-vector framework," in Proc. Interspeech, (Singapore), Sept. 2014.

• R. Gupta, T. Guha, N. Malandrakis, M. V. Segbroeck, B. Xiao, M. P. Black, A. Potamianos, and S. S. Narayanan, "Multimodal prediction of affective dimensions and depression in human-computer interactions," in Proc. Intl. Audio Visual Emotion Challenge and Workshop, Orlando, Florida, Nov. 2014.

• M. Perakakis and A. Potamianos, "An affective evaluation tool using brain signals," in Proc. Intl. Conf. on Intelligent User Interfaces (companion volume), Santa Monica, CA, pp. 105-106, ACM, Mar. 2013.

• N. Malandrakis, I. Elias, V. Prokopi, A. Potamianos, and S. S. Narayanan, "Deeppurple: Lexical, string and affective feature fusion for sentence-level semantic similarity estimation," in Proc. 2nd Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity, pp. 103-108, Association for Computational Linguistics, June 2013.

• N. Malandrakis, A. Potamianos, E. Iosif, and S. S. Narayanan, "Distributional semantic models for affective text analysis," IEEE Transactions on Audio, Speech and Language Processing, vol. 21, pp. 2379-2392, Nov. 2013.

• N. Malandrakis, A. Potamianos, and S. Narayanan, "Continuous models of affect from text using n-grams," in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Vancouver, Canada, May 2013.

• N. Malandrakis, S. Sundaram, and A. Potamianos, "Affective classification of generic audio clips using regression models," in Proc. Interspeech, Lyon, France, Aug. 2013.

• M. Perakakis and A. Potamianos, "Affective evaluation of a mobile multimodal dialogue system using brain signals," in Proc. IEEE/ACM Workshop on Spoken Language Technology, Miami, Florida, Dec. 2012.

• S. Yildirim, S. Narayanan, and A. Potamianos, "Detecting Emotional State of a Child in a Conversational Computer Game ,"Computer, Speech and Language , vol. 25, no. 1, pp. 29-44, Jan. 2011.

• N. Malandrakis, A. Potamianos, G. Evangelopoulos and A. Zlatintsi, "A supervised approach to movie emotion tracking,"in Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, Apr. 2011.

• N. Malandrakis, A. Potamianos, E. Iosif and S. Narayanan, "Kernel models for affective lexicon creation,"in Proc. Interspeech , Florence, Italy, Aug. 2011.

• S. Yildirim, C. Lee, S. Lee, A. Potamianos, and S. Narayanan, "Detecting politeness and frustration state of a child in a conversational computer game ,'' in Proc. European Conf. on Speech Communication and Technology, Lisbon, Portugal, Sept. 2005.

Multimedia Processing

• T. Kouzelis, G. Bastas, A. Katsamanis, and A. Potamianos, "Efficient Audio Captioning Transformer with Patchout and Text Guidance,"in arXiv preprint arXiv:2304.02916, Apr. 2023.

• M. N. Minaidi, C. Papaioannou, and A. Potamianos, "Self-Attention Based Generative Adversarial Networks For Unsupervised Video Summarization,"in Proc. European Signal Processing Conference (EUSIPCO), (Helsinki, Finland), pp. 571-575, Sept. 2023.

• C. Papaioannou, E. Benetos, and A. Potamianos, "From West to East: Who can understand the music of the others better?,"in Proc. Internat. Soc. for Music Information Retrieval (ISMIR), (Milan, Italy), Nov. 2023.

• C. Sartzetaki, G. Paraskevopoulos, and A. Potamianos, "Extending Compositional Attention Networks for Social Reasoning in Videos,"in Proc. Interspeech, (Incheon, Korea), pp. 1116-1120, Sept. 2022.

• C. Papaioannou, I. Valiantzas, T. Giannakopoulos, M. Kaliakatsos-Papakostas, and A. Potamianos, "A Dataset for Greek Traditional and Folk Music: Lyra,"in Proc. Internat. Soc. for Music Information Retrieval (ISMIR), (Bengaluru, India), Dec. 2022.

• A. Zlatintsi, E.Iosif, P. Maragos, and A. Potamianos, "Audio salient event detection and summarization using audio and text modalities," in Proc. European Signal Process. Conf., Nice, France, May 2015.

• P. Koutras, A. Zlatintsi, E.Iosif, A. Katsamanis, P. Maragos, and A. Potamianos, "Predicting audio-visual salient events based on visual, audio and text modalities for movie summarization," in Proc. Internat.Conf. on Image Processing, Quebec City, Canada, Sept. 2015.

• A. Zlatintsi, P. Koutras, N. Efthymiou, P. Maragos, A. Potamianos, and K. Pastra, "Quality evaluation of computational models for movie summarization," in Proc. Intl. Workshop on Quality of Multimedia Experience (QoMEX), (Costa Navarino, Messinia, Greece), May 2015.

• G. Evangelopoulos, A. Zlatintsi, A. Potamianos, P. Maragos, K. Rapantzikos, G. Skoumas, and Y. Avrithis, "Multimodal saliency and fusion for movie summarization based on aural, visual, and textual attention," IEEE Transactions on Multimedia, vol. 15, pp. 1553-1568, Nov. 2013.

• A. Zlatintsi, P. Maragos, A. Potamianos, and G. Evangelopoulos, "A saliency-based approach to audio event detection and summarization," in Proc. European Signal Process. Conf., Aug. 2012.

• G. Evangelopoulos, A. Zlatintsi, G. Skoumas, K. Rapantzikos, A. Potamianos, P. Maragos, and Y. Avrithis, "Video Event Detection and Summarization Using Audio, Visual and Text Saliency ," in Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, Apr. 2009.

• G. Evangelopoulos, K. Rapatzikos, P. Maragos, Y. Avrithis, A. Potamianos, "Audiovisual Attention Modeling and Salient Event Detection", in Multimodal Processing and Interaction: Audio, Video, Text, Springer-Verlag, 2008.

• A. Potamianos and M. Perakakis, "Human-Computer Interfaces to Multimedia Content: A Review,'' in Multimodal Processing and Interaction: Audio, Video, Text, Springer-Verlag, 2008.

• G. Evangelopoulos, K. Rapantzikos, A. Potamianos, P. Maragos, A. Zlatintsi and Y. Avrithis, "Movie Summarization Based On Audio-Visual Saliency Detection ", in Proc. Intl Conference on Image Processing (ICIP), San Diego, California, Oct. 2008.

• P. Maragos, A. Potamianos and P. Gros (eds), Multimodal Processing and Interaction: Audio, Video, Text , Springer-Verlag, 2008.

• S. Siltanen et al, "Multimodal user interface for augmented assembly ,'' in Proc. Intern. Workshop on Multimedia Signal Processing, Chania, Greece, Oct. 2007.

• A. Potamianos, E. Fosler-Lussier, E. Ammicht, and M. Perakakis, "Information seeking spoken dialogue systems - Part II: Multimodal dialogue ,'' IEEE Transactions on Multimedia, Vol. 9, pp. 550 - 566, April 2007.

Other

• E. Georgiou, K. Kritsis, G. Paraskevopoulos, A. Katsamanis, V. Katsouros, and A. Potamianos, "Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss,"in Proc. IEEE/ACM Workshop on Spoken Language Technology, (Doha, Qatar), pp. 977-983, July 2023.

• G. Paraskevopoulos, E. Tzinis, E.-V. Vlatakis-Gkaragkounis, and A. Potamianos, "Pattern search MDS," arXiv preprint arXiv:1806.00416, Mar. 2018.

• A. Fergadis, C. Baziotis, D. Pappas, H. Papageorgiou, and A. Potamianos, "Hierarchical bidirectional attention-based RNN in BioCreative VI precision medicine track, document triage task," in Proc. BioCreative Challenge Evaluation Workshop, Bethesda, Maryland, Oct. 2017.

• D. Nion, K. Mokios, N. Sidiropoulos, A. Potamianos, "Batch and Adaptive PARAFAC-Based Blind Separation of Convolutive Speech Mixtures," IEEE Transactions on Audio, Speech and Language Processing, vol. 18, no. 6, pp. 1193 - 1207, Aug. 2010.

• K. Mokios, A. Potamianos, and N.  Sidiropoulos, "On the Effectiveness of PARAFAC-Based Estimation in Blind Speech Separation ", in Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, Nevada, Apr. 2008.

• A. Katsamanis, P. Tsiakoulis, P. Maragos, and A. Potamianos, "Investigations in articulatory synthesis ,'' in Proc. Intenat. Conf. on Phonetics, Saarbrucken, Germany, Aug. 2007.

• K. Mokios, N. Sidiropoulos, and A. Potamianos, "Blind speech separation algorithm using PARAFAC and integer least squares ,'' in Proc. Internat. Conf. on Acoust., Speech, and Signal Process., Toulouse, France, May 2006.

• P. Karageorgakis, A. Potamianos, and I. Klasinas, "Towards incorporating language morphology into statistical machine translation systems ,'' in Proc. Automatic Speech Recogn. and Underst. Workshop, Cancun, Mexico, Dec. 2005.

• A. Pargellis and A. Potamianos, "Cross-domain classification using generalized domain acts ,'' in Internat. Conf. Speech Language Processing, Beijing, China, Oct. 2000.

• J. Diamesis and A. Potamianos, "Tridiagonal state-space realization of a class of 2-D transfer functions,'' in Proc. of the 25th Conf. on Information Sciences and Systems, Baltimore, MD, pp. 249-253, Mar. 1991.