[portrait]


Kornel Laskowski

Former Student (c/o R Stern)
Language Technologies Institute
School of Computer Science
Carnegie Mellon University



kornel AT cs DOT cmu DOT edu
Carnegie Mellon University
407 S Craig St, SCR 218
Pittsburgh PA, 15213
USA
Phone: +1 412 996 3042


Kornel Laskowski



Current interests

computational semiotics in multiparty conversation; acoustic signal processing for glottal modeling; automatic vocal activity recognition; structural resonance modeling of the cochlear shelf; physical modeling for speech synthesis; computational models for speech acquisition.


Education

Ph.D. in Computer Science, Carnegie Mellon University, February 2011.
M.S. in Language Technologies, Carnegie Mellon University, May 2002.
B.A.Sc. in Engineering Physics, University of British Columbia, May 1996.


Recent Employment

Principal Speech Scientist, Voci Technologies, Inc., USA, Aug 2012 - (now).
Gästforskare, Institutionen för Lingvistik, Stockholms Universitetet, Sweden, Apr 2016 - (now).
Forskare, Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden, Sep 2010 - Jun 2011.
Research Assistant, Language Technologies Institute, Carnegie Mellon University, USA, Jun 2009 - Aug 2009.
Wissenschaftlicher Mitarbeiter, Lehrstuhl für Kognitive Systeme, Universität Karlsruhe, Germany, Nov 2007 - May 2009,
                    Mensch - Maschine - Emotion (SS 2008) with Tanja Schultz,
                    Biosignale und Benutzerschnittstellen (WS 2007/2008) with Tanja Schultz.
Research Assistant, Language Technologies Institute, Carnegie Mellon University, USA, Dec 2006 - Oct 2007.
Teaching Assistant, Computer Science Department, Carnegie Mellon University, USA, Jan 2004 - May 2004,
                    15-782 Artificial Neural Networks with Dave Touretzky.
Teaching Assistant, Electrical and Computer Engineering, Carnegie Mellon University, USA, Aug 2004 - Dec 2004,
                    18-493 Electroacoustics with Rich Stern and Tom Sullivan.
Wissenschaftlicher Mitarbeiter, Institut für Theoretische Informatik, Universität Karlsruhe, Germany, Jul 2002 - Nov 2006.
Research Assistant, Language Technologies Institute, Carnegie Mellon University, USA, Aug 2000 - Jun 2002.
Telecommunications Software Engineer, Nortel Networks, Canada, Jun 1996 - Jul 2000.


Publications

Marcin Włodarczak, Kornel Laskowski, Mattias Heldner and Kätlin Aare (2017), Improving prediction of speech activity using multi-participant respiratory state, In the proceedings of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH2017), Stockholm, Sweden, 20-24 August, pp1666-1670. doi:10.21437/Interspeech.2017-1176 [poster]

Kornel Laskowski (2016), A Framework for the Automatic Inference of Stochastic Turn-Taking Styles, In the proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL2016), Los Angeles CA, USA, 13-15 September, pp202-211. doi:10.18653/v1/W16-3624 [poster]

Kornel Laskowski (2015), Auto-Imputing Radial Basis Functions for Neural-Network Turn-Taking Models, In the proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH2015), Dresden, Germany, 06-10 September, pp1820-1824. doi not assigned [poster]

Kornel Laskowski and Anna Hjalmarsson (2015), An Information-Theoretic Framework for Automated Discovery of Prosodic Cues to Conversational Structure, In the proceedings of the 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2015), Brisbane, Australia, 19-24 April, pp5376-5380. doi:10.1109/ICASSP.2015.7178998 [poster]

Kornel Laskowski (2014), On the Conversant-Specificity of Stochastic Turn-Taking Models, In the proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH2014), Singapore, 14-18 September, pp2026-2030. doi not assigned [poster]

Kornel Laskowski (2012), Exploiting Loudness Dynamics in Stochastic Models of Turn-Taking, In the proceedings of the 4th IEEE Workshop on Spoken Language Technology (SLT2012), Miami FL, USA, 2-5 December, pp79-84. doi:10.1109/SLT.2012.6424201 [poster]

Kornel Laskowski, Mattias Heldner and Jens Edlund (2012), On the Dynamics of Overlap in Multi-Party Conversation, In the proceedings of the 13th Annual Conference of the International Speech Communication Association (INTERSPEECH2012), Portland OR, USA, 9-13 September, pp847-850. doi not assigned [slides]

Kornel Laskowski and Elizabeth Shriberg (2012), Corpus-Independent History Compression for Stochastic Turn-Taking Models, In the proceedings of the 37th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2012), Kyoto, Japan, 25-30 March, pp4937-4940. doi:10.1109/ICASSP.2012.6289027 [poster]

Kornel Laskowski (2012), Transfer Cross Entropy for Fast Sociometric Inference in Longitudinal Collections of Multi-Party Conversation, In the proceedings of the 37th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2012), Kyoto, Japan, 25-30 March, pp2189-2192. doi:10.1109/ICASSP.2012.6288347 [poster]

Kornel Laskowski, Jens Edlund and Mattias Heldner (2011), Incremental Learning and Forgetting in Stochastic Turn-Taking Models, In proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH2011), Firenze, Italy, 27-31 August, pp2069-2072. doi not assigned [poster] [software (to appear)]

Kornel Laskowski and Qin Jin (2011), Harmonic Structure Transform for Speaker Recognition, In proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH2011), Firenze, Italy, 27-31 August, pp365-368. doi not assigned [slides]

Anna Hjalmarsson and Kornel Laskowski (2011), Measuring Final Lengthening for Speaker-Change Prediction, In proceedings of the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH2011), Firenze, Italy, 27-31 August, pp2065-2068. doi not assigned [poster] [software]

Mattias Heldner, Jens Edlund, Anna Hjalmarsson and Kornel Laskowski (2011), Very Short Utterances and Timing in Turn-Taking, In proceedings of the the 12th Annual Conference of the International Speech Communication Association (INTERSPEECH2011), Firenze, Italy, 27-31 August, pp2837-2840. doi not assigned [poster]

Kornel Laskowski, Jens Edlund and Mattias Heldner (2011), A Single-Port Non-Parametric Model of Turn-Taking in Multi-Party Conversation, In proceedings of the 36th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2011), Praha, Czech Republic, 22-27 May, pp5600-5603. doi:10.1109/ICASSP.2011.5947629 [poster] [software]

Kornel Laskowski (2011), Predicting, Detecting and Explaining the Occurrence of Vocal Activity in Multi-Party Conversation, PhD Thesis (CMU-LTI-11-001), Language Technologies Institute, Carnegie Mellon University, Pittsburgh PA, USA, 23 February. [slides]

Kornel Laskowski, Mattias Heldner and Jens Edlund (2010), Preliminaries to an Account of Multi-Party Conversational Turn-Taking as an Antiferromagnetic Spin Glass, In proceedings of the Workshop on Modeling Human Communication Dynamics at the 24th Neural Information Processing Systems Conference (NIPS2010), Vancouver, Canada, 10-11 December, pp46-49. doi not assigned [poster]

Kornel Laskowski (2010), Modeling Norms of Turn-Taking in Multi-Party Conversation, In proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (ACL2010), Uppsala, Sweden, 11-16 July, pp999-1008. doi not assigned [slides] [errata 1, 03 Nov 2010] [software]

Kornel Laskowski and Qin Jin (2010), Modeling Prosody for Speaker Recognition: Why Estimating Pitch May Be a Red Herring, In proceedings of the 7th ISCA Speaker and Language Recognition Workshop (ODYSSEY2010), Brno, Czech Republic, 28 June - 01 July. [slides]

Kornel Laskowski and Jens Edlund (2010), A Snack Implementation and Tcl/Tk Interface to the Fundamental Frequency Variation Spectrum Algorithm, In proceedings of the 7th ELRA International Conference on Language Resources and Evaluation (LREC2010), La Valletta, Malta, 17-23 May, pp3742-3749. [poster]

Kornel Laskowski (2010), A Frame-Synchronous Prosodic Decoder for Text-Independent Dialog Act Recognition, In proceedings of the 5th ISCA International Conference on Speech Prosody (SP2010), Chicago IL, USA, 11-14 May. [poster]

Kornel Laskowski and Elizabeth Shriberg (2010), Comparing the Contributions of Context and Prosody in Text-Independent Dialog Act Recognition, In proceedings of the 35th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2010), Dallas TX, USA, 14-19 March, pp5374-5377. [poster]

Kornel Laskowski (2010), Finding Emotionally Involved Speech Using Implicitly Proximity-Annotated Laughter, In proceedings of the 35th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2010), Dallas TX, USA, 14-19 March, pp5226-5229. [poster]

Qin Jin, Runxin Li, Qian Yang, Kornel Laskowski and Tanja Schultz (2010), Speaker Identification with Distant Microphone Speech, In proceedings of the 35th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2010), Dallas TX, USA, 14-19 March, pp4518-4521. [poster]

Kornel Laskowski (2009), Detecting Attempts at Humor in Multiparty Meetings, In proceedings of the 3rd IEEE International Conference on Semantic Computing (ICSC2009), Berkeley CA, USA, 14-16 September, pp9-16. [slides]

Kornel Laskowski and Elizabeth Shriberg (2009), Modeling Other Talkers for Improved Dialog Act Recognition in Meetings, In proceedings of the 10th Annual Conference of the International Speech Communication Association (INTERSPEECH2009), Brighton, UK, 6-10 September, pp2783-2786. [slides]

Kornel Laskowski, Mattias Heldner and Jens Edlund (2009), A General-Purpose 32 ms Prosodic Vector for Hidden Markov Modeling, In proceedings of the 10th Annual Conference of the International Speech Communication Association (INTERSPEECH2009), Brighton, UK, 6-10 September, pp724-727. [slides] [software]

Kornel Laskowski, Mattias Heldner and Jens Edlund (2009), Exploring the Prosody of Floor Mechanisms in English Using the Fundamental Frequency Variation Spectrum, In proceedings of the 17th European Signal Processing Conference (EUSIPCO2009), Glasgow, UK, 24-28 August, pp2539-2543. [poster]

Kornel Laskowski (2009), Contrasting Emotion-Bearing Laughter Types in Multiparticipant Vocal Activity Detection for Meetings. In proceedings of the 34th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009), Taipei, Taiwan, 19-24 April, pp4765-4768. [poster]

Kornel Laskowski and Qin Jin (2009), Modeling Instantaneous Intonation for Speaker Identification Using the Fundamental Frequency Variation Spectrum. In proceedings of the 34th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009), Taipei, Taiwan, 19-24 April, pp4541-4544. [poster]

Kornel Laskowski (2008), Modeling Vocal Interaction for Text-Independent Detection of Involvement Hotspots in Multi-Party Meetings. In proceedings of the 2nd IEEE/ISCA/ACL Workshop on Spoken Language Technology (SLT2008), Goa, India, 15-18 December, pp81-84. [poster]

Kornel Laskowski and Tanja Schultz (2008), Recovering Participant Identities in Meetings from a Probabilistic Description of Vocal Interaction. In proceedings of the 9th Annual Conference of the International Speech Communication Association (INTERSPEECH2008), Brisbane, Australia, 22-26 September, pp82-85. [slides]

Kornel Laskowski and Tanja Schultz (2008), Detection of Laughter-in-Interaction in Multichannel Close-Talk Microphone Recordings of Meetings. In Machine Learning for Multimodal Interaction (A. Popescu-Belis and R. Stiefelhagen, eds.), Springer Berlin/Heidelberg (Lecture Notes in Computer Science 5237), pp149-160. Presented at the 5th Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI2008), Utrecht, The Netherlands, 08-10 September. [slides]

Mattias Heldner, Jens Edlund, Kornel Laskowski, and Antoine Pelcé (2008), Prosodic Features in the Vicinity of Silences and Overlaps. In proceedings of the 10th Nordic Conference on Prosody, Helsinki, Finland, 04-06 August, pp95-105. [slides]

Kornel Laskowski, Matthias Wölfel, Mattias Heldner, and Jens Edlund (2008), Computing the Fundamental Frequency Variation Spectrum in Conversational Spoken Dialogue Systems. In proceedings of the 155th Meeting of the Acoustical Society of America, 5th EAA Forum Acusticum, and 9th SFA Congrés Français d'Acoustique (Acoustics2008), Paris, France, 29 June - 04 July, pp3305-3310. [slides]

Kornel Laskowski, Mari Ostendorf, and Tanja Schultz (2008), Modeling Vocal Interaction for Text-Independent Participant Characterization in Multi-Party Conversation. In proceedings of the 9th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL2008) Columbus OH, USA, 19-20 June, pp148-155. [slides]

Kornel Laskowski, Mattias Heldner, and Jens Edlund (2008), The Fundamental Frequency Variation Spectrum. In proceedings of the 21st Swedish Phonetics Conference (Fonetik 2008), Gothenburg, Sweden, 11-13 June, pp29-32. [slides]

Susanne Burger, Kornel Laskowski, and Matthias Wölfel (2008), A Comparative Cross-Domain Study of the Occurrence of Laughter in Meeting and Seminar Corpora. In proceedings of the 6th International Conference on Language Resources and Evaluation (LREC2008), Marrakech, Morocco, 28-30 May. [errata, 19.05.2008 0610hrs GMT] [slides]

Kornel Laskowski, Jens Edlund, and Mattias Heldner (2008), Learning Prosodic Sequences Using the Fundamental Frequency Variation Spectrum. In proceedings of the 4th ISCA International Conference on Speech Prosody (SP2008), Campinas, Brazil, 06-09 May, pp151-154. [poster]

Kornel Laskowski, Jens Edlund, and Mattias Heldner (2008), An Instantaneous Vector Representation of Delta Pitch for Speaker-Change Prediction in Conversational Dialogue Systems. In proceedings of the 33rd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2008), Las Vegas NV, USA, 30 March - 04 April, pp5041-5044. [poster]

Kornel Laskowski and Tanja Schultz (2007), A Supervised Factorial Acoustic Model for Simultaneous Multiparticipant Vocal Activity Detection in Close-Talk Microphone Recordings of Meetings. LTI Technical Report CMU-LTI-07-017, Carnegie Mellon University, Pittsburgh PA, USA, 21 December.

Kornel Laskowski and Susanne Burger (2007), Annotation Guide for Laughter in Multi-Party Conversation. LTI Technical Report CMU-LTI-07-013, Carnegie Mellon University, Pittsburgh PA, USA, 11 December.

Kornel Laskowski, Christian Fügen, and Tanja Schultz (2007), Simultaneous Multispeaker Segmentation for Automatic Meeting Recognition. In proceedings of the 15th EURASIP European Signal Processing Conference (EUSIPCO2007), Poznań, Poland, 03-07 September, pp1294-1298. [slides]

Kornel Laskowski, Mari Ostendorf, and Tanja Schultz (2007), Modeling Vocal Interaction for Text-Independent Classification of Conversation Type. In proceedings of the 8th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL2007) Antwerpen, Belgium, 01-02 September, pp194-201. [slides]

Kornel Laskowski and Susanne Burger (2007), Analysis of the Occurrence of Laughter in Meetings. In proceedings of the 8th Annual Conference of the International Speech Communication Association (INTERSPEECH2007), Antwerpen, Belgium, 27-31 August, pp1258-1261. [slides]

Kornel Laskowski and Susanne Burger (2007), On the Correlation between Perceptual and Contextual Aspects of Laughter in Meetings. In proceedings of the Workshop on the Phonetics of Laughter at the 16th International Congress of Phonetic Sciences (ICPhS2007), Saarbrücken, Germany, 04-05 August, pp55-60. [slides]

Kornel Laskowski and Tanja Schultz (2007), Modeling Vocal Interaction for Segmentation in Meeting Recognition. In Machine Learning for Multimodal Interaction (A. Popescu-Belis, S. Renals, and H. Bourlard, eds.), Springer Berlin/Heidelberg (Lecture Notes in Computer Science 4892), pp259-270. Presented at the 4th Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI2007), Brno, Czech Republic, 28-30 June. [slides]

Kornel Laskowski and Tanja Schultz (2007), A Geometric Interpretation of Non-Target-Normalized Maximum Cross-channel Correlation for Vocal Activity Detection in Meetings. In proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT2007); Companion Volume, Short Papers, Rochester NY, USA, 22-27 April, pp89-92. [poster]

Christian Fügen, Shajith Ikbal, Florian Kraft, Kenichi Kumatani, Kornel Laskowski, John McDonough, Mari Ostendorf, Sebastian Stüker, and Matthias Wölfel (2006), The ISL RT-06S Speech-to-Text System. In Machine Learning for Multimodal Interaction (S. Renals, S. Bengio, and J. Fiscus, eds.), Springer Berlin/Heidelberg (Lecture Notes in Computer Science 4299), pp407-418. Presented at the 3rd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms (MLMI2006), Washington DC, USA, 01-03 May. [SpringerLink]

Kornel Laskowski (2006), Vocal Interaction in Multiparty Conversation (PhD thesis proposal). Carnegie Mellon University, Pittsburgh PA, USA, 09 November. [slides; audio: NFA, NFB, NFC, NFD, NFE, FF]

Anton Batliner, Stefan Steidl, Björn Schuller, Dino Seppi, Kornel Laskowski, Thurid Vogt, Laurence Devillers, Laurence Vidrascu, Noam Amir, Loic Kessous, Vered Aharonson (2006), Combining Efforts for Improving Automatic Classification of Emotional User States. In proceedings of the 5th Slovenian and 1st International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, 09-10 October.

Daniel Neiberg, Kjell Elenius, and Kornel Laskowski (2006), Emotion Recognition in Spontaneous Speech Using GMMs. In proceedings of the 9th ISCA International Conference on Spoken Language Processing (INTERSPEECH2006), Pittsburgh PA, USA, 17-21 September, pp809-812.

Christian Fügen, Matthias Wölfel, John W. McDonnough, Shajith Ikbal, Florian Kraft, Kornel Laskowski, Mari Ostendorf, Sebastian Stüker, and Kenichi Kumatani (2006), Advances in Lecture Recognition: The ISL RT-06S Evaluation System. In proceedings of the 9th ISCA International Conference on Spoken Language Processing (INTERSPEECH2006), Pittsburgh PA, USA, 17-21 September, pp1229-1232.

Daniel Neiberg, Kjell Elenius, Inger Karlsson, and Kornel Laskowski (2006), Emotion Recognition in Spontaneous Speech. In proceedings of the 19th Swedish Phonetics Conference (Fonetik 2006), Lund, Sweden, 07-09 June, pp101-104.

Kornel Laskowski and Susanne Burger (2006), Annotation and Analysis of Emotionally Relevant Behavior in the ISL Meeting Corpus. In proceedings of the 5th ELRA International Conference on Language Resources and Evaluation (LREC2006), Genoa, Italy, 24-26 May. [slides] [pilot work]

Kornel Laskowski and Tanja Schultz (2006), Unsupervised Learning of Overlapped Speech Model Parameters for Multichannel Speech Activity Detection in Meetings. In proceedings of the 31st IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2006), Toulouse, France, 14-19 May, pp993-996. [poster: p1, p2]

Kornel Laskowski, Qin Jin, and Tanja Schultz (2004), Crosscorrelation-based Multispeaker Speech Activity Detection. In proceedings of the 8th ISCA International Conference on Spoken Language Processing (INTERSPEECH2004), Jeju Island, South Korea, 04-08 October, pp973-976. [poster]

Florian Metze, Qin Jin, Christian Fügen, Kornel Laskowski, Yue Pan, and Tanja Schultz (2004), Issues in Meeting Transcription - The ISL Meeting Transcription System. In proceedings of the 8th ISCA International Conference on Spoken Language Processing (INTERSPEECH2004), Jeju Island, South Korea, 04-08 October, pp1709-1712.

Qin Jin, Kornel Laskowski, Tanja Schultz, and Alex Waibel (2004), Speaker Segmentation and Clustering in Meetings. In proceedings of the NIST RT-04 Spring Meeting Recognition Evaluation Workshop at the 29th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2004), Montreal, Canada, 17 May.

Tanja Schultz, Qin Jin, Kornel Laskowski, Alicia Tribble, and Alex Waibel (2002), Improvements in Non-verbal Cue Identification Using Multilingual Phone Strings. In proceedings of the Workshop on Speech-to-Speech Translation: Algorithms and Systems at the 40th Annual Meeting of the Association for Computational Linguistics (ACL2002), Philadelphia PA, USA, 07-12 July, pp101-108.

Alon Lavie, Florian Metze, Roldano Cattoni, Erica Constantini, et al (2002), A Multi-Perspective Evaluation of the NESPOLE! Speech-to-Speech Translation System. In proceedings of the Workshop on Speech-to-Speech Translation: Algorithms and Systems at the 40th Annual Meeting of the Association for Computational Linguistics (ACL2002), Philadelphia PA, USA, 07-12 July, pp121-128.

Tanja Schultz, Qin Jin, Kornel Laskowski, Alicia Tribble, and Alex Waibel (2002), Speaker, Accent, and Language Identification using Multilingual Phone Strings. In proceedings of the 2nd International Conference on Human Language Technology Research (HLT2002) San Diego CA, USA.

Florian Metze, John McDonough, Hagen Soltau, Alex Waibel, Alon Lavie, Susanne Burger, Chad Langley, Kornel Laskowski, Lori Levin, Tanja Schultz, Fabio Pianesi, Roldano Cattoni, Gianni Lazzari, Nadia Mana and Emanuele Pianta. The NESPOLE! Speech-to-Speech Translation System. In proceedings of the 2nd International Conference on Human Language Technology Research (HLT2002) San Diego CA, USA.



Last modified: Mon 6 May 2019 2233hrs GMT