Publication Search Results

TitleAuthorBibliographicDateGroupsort descendingLinks
Incorporating Tandem/HATs MLP Features into SRI's Conversational Speech Recognition SystemQ. Zhu, A. Stolcke, B. Y. Chen, and N. MorganProceedings of the EARS RT-04F Workshop, Palisades, New York, November 2004.November 2004Speech[PDF]

The ICSI Meeting Corpus: Close-Talking and Far-Field, Multi-Channel Transcriptions for Speech and Language ResearchersJ. A. EdwardsProceedings of the Workshop on Compiling and Processing Spoken Language Corpora at the Fourth International Conference on Language Resources and Evaluation (LREC 2004), pp. 8-11May 2004Speech[PDF]

Auditory-Based Automatic Speech RecognitionW. Hemmert, M. Holmberg, and D. GelbartProceedings of ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing, Jeju, Korea, October 2004.October 2004Speech[PDF]

Vocabulary and Language Model Adaptation Using Information RetrievalB. Bigi, Y. Huang, and R. De MoriProceedings of International Conference on Spoken Language Processing, Jeju, Korea, October 2004.October 2004Speech[PDF]

Learning Long-Term Temporal Features in LVCSR Using Neural NetworksB. Chen, Q. Zhu, and N. MorganProceedings of International Conference on Spoken Language Processing, Jeju, Korea, October 2004.October 2004Speech[PDF]

On Using MLP Features in LVCSRQ. Zhu, B. Chen, N. Morgan. and A. StolckeProceedings of International Conference on Spoken Language Processing, Jeju, Korea, October 2004.October 2004Speech[PDF]

Direct Modeling of Prosody: An Overview of Applications in Automatic Speech ProcessingE. Shriberg and A. StolckeProceedings of the International Conference on Speech Prosody, Nara, Japan, March 2004.March 2004Speech[PDF]

Prosody Modeling for Automatic Speech Recognition and UnderstandingE. Shriberg and A. StolckeMathematical Foundations of Speech and Language Modeling, M. Johnson, M. Ostendorf, S. Khudanpur, R. Rosenfeld (eds.), Volume 138 in IMA Volumes in Mathematics and its Applications, pp. 105-114, Springer-Verlag. 2004Speech[PDF]

Qualcomm-ICSI-OGI Features for ASRA. Adami, L. Burget, S. Dupont, H. Garudadri, F. Grezl, H. Hermansky, P. Jain, S. Kajarekar, N. Morgan, and S. SivadasProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoSeptember 2002Speech[PDF]

A New Speaker Change Detection Method for Two-Speaker SegmentationA. Adami, S. Kajarekar, and H. HermanskyProceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, FloridaMay 2002Speech[PDF]

Unknown-Multiple Speaker Clustering Using HMMJ. Ajmera, H. Bourlard, I. Lapidot, and I. McCowanProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoMay 2002Speech
Prosodic Cues For Emotion Recognition In Communicator DialogsJ.C. AngM.S. Thesis, University of California at BerkeleyDecember 2002Speech[PDF]

Prosody-Based Automatic Detection of Annoyance and Frustration in Human-Computer DialogJ. Ang, R. Dhillon, A. Krupski, E. Shriberg, and A. StolckeProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoSeptember 2002Speech
Prosody-Based Automatic Detection of Punctuation and Interruption Events in the ICSI Meeting Recorder CorpusD. BaronM.S. Thesis, University of California at BerkeleyMay 2002Speech[PDF]

Automatic Punctuation and Disfluency Detection in Multi-Party Meetings Using Prosodic and Lexical CuesD. Baron, E. Shriberg, and A. StolckeProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, Colorado, pp. 949-952September 2002Speech[PDF]

A Syllable, Articulatory-Feature, and Stress-Accent Model of Speech RecognitionS. ChangPh.D. Thesis, University of California at Berkeley. Also ICSI Technical Report TR-02-007September 2002Speech[PDF]

Reducing the Effect of Room Acoustics on Human-Computer InteractionD. GelbartProceedings of the Applied Voice Input/Output Society (AVIOS 2002), San Jose, CaliforniaMay 2002Speech[PDF]

Double the Trouble: Handling Noise and Reverberation in Far-Field Automatic Speech RecognitionD. Gelbart and N. MorganProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoSeptember 2002Speech[PDF]

The Relation of Stress Accent to Pronunciation Variation in Spontaneous American English DiscourseS. Greenberg, H.M. Carvey, and L. HitchcockProceedings of the International Conference on Speech Prosody 2002, Aix-en-Provence, FranceApril 2002Speech
Robust Speech Recognition Based on Spectro-Temporal ProcessingM. KleinschmidtPh.D Dissertation, University of Oldenberg, Germany 2002Speech
Spectro-temporal Gabor Features as a Front End for Automatic Speech RecognitionM. KleinschmidtProceedings of the Triennial Forum Acusticum 2002, Seville, SpainSeptember 2002Speech[PDF]

Improving Word Accuracy with Gabor Feature ExtractionM. Kleinschmidt and D. GelbartProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoSeptember 2002Speech[PDF]

What's New in Government-Sponsored Speech Recognition ResearchN. MorganSpeech Technology Magazine, Vol. 7, No. 5September 2002Speech
Hierarchical Tandem Feature ExtractionS. Sivadas and H. HermanskyProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, FloridaMay 2002Speech[PDF]

Speech Modeling Using Variational Bayesian Mixture of GaussiansP. SomervuoProceedings of the 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, ColoradoSeptember 2002Speech[PDF]

Using Prosodic and Lexical Information for Speaker IdentificationF. Weber, L. Manganaro, B. Peskin, and E. ShribergProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), Orlando, FloridaMay 2002Speech[PDF]

Combining Bottom-Up and Top-Down Constraints for Robust ASR: The Multiscore DecoderJ. Barker, M. Cooke, and D. EllisProceedings of the Workshop on Consistent and Reliable Acoustic Cues (CRAC-2001), Aalborg, DenmarkSeptember 2001Speech
Chapter 17: The Transcription of DiscourseJ. EdwardsThe Handbook of Discourse Analysis, D. Shriffrin, D. Tannen and H. Hamilton, eds. Oxford: Blackwell, pp. 321-348 2001Speech
Investigations Into Tandem Acoustic Modeling for the Aurora TaksD.P.W. Ellis and M. ReyesProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech
Tandem Acoustic Modeling in Large-Vocabulary RecognitionD. Ellis, R. Singh, and S. SivadasProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, UtahMay 2001Speech
The Relation Between Stress Accent and Vocalic Identity in Spontaneous American English DiscourseS. Greenberg, S. Chang, and L. HitchcockProceedings of ISCA Workshop on Prosody in Speech Recognition and Understanding, Red Bank, New JerseyOctober 2001Speech
A Study of Two Dimensional Linear Descriminants For ASRS. Kajarekar, B. Yegnanarayana, and H. HermanskyProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, UtahMay 2001Speech
Multispeaker Speech Activity Detection for the ICSI Meeting RecorderT. Pfau, D. Ellis, and A. StolckeProceedings of Automatic Speech Recognition and Understanding Workshop (ASRU 2001), Madonna di Campiglio, Italy, pp. 107-110December 2001Speech[PDF]

Evaluating Long-term Spectral Subtraction for Reverberant ASRD. Gelbart and N. MorganProceedings of the Automatic Speech Recognition and Understanding Workshop (ASRU 2001), Madonna di Campiglio, ItalyDecember 2001Speech[PDF]

Relating Frame Accuracy with Word Error in Hybrid ANN-HMM ASRM. ShireProceedings of the 6th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

Can Prosody Aid the Automatic Processing of Multi-Party Meetings? Evidence from Predicting Punctuation, Disfluencies, and Overlapping SpeechE. Shriberg, A. Stolcke, and D. BaronProceedings of the ISCA Tutorial and Research Workshop on Prosody in Speech Recognition and Understanding, Red Bank, New JerseyOctober 2001Speech[PDF]

SpeechCorder, The Portable Meeting RecorderA. Janin and N. MorganProceedings of the Workshop on Hands-Free Speech Communication, Kyoto, JapanApril 2001Speech[PDF]

Meeting RecorderA. JaninProceedings of the Applied Voice Input/Output Society, San Jose, CaliforniaApril 2001Speech[PDF]

Robust ASR Front-End Using Spectral-Based and Discriminant Features: Experiments on the Aurora TasksC. Benitez, L. Burget, B. Chen, S. Dupont, H. Garudadri, H. Hermansky, P. Jain, S. Kajarekar, and S. SivadasProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, Denmark, pp. 429-432September 2001Speech[PDF]

Observations on Overlap: Findings and Implications for Automatic Processing of Multi-Party ConversationE. Shriberg, A. Stolcke, and D. BaronProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

An Elitist Approach to Articulatory-Acoustic Feature ClassificationS. Chang, S. Greenberg, and M. WesterProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

From Here to Utility - Melding Phonetic Insight with Speech TechnologyS. GreenbergProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

Whither Speech Technology? - A Twenty-First Century PerspectiveS. GreenbergProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

The Relation Between Speech Intelligibility and the Complex Modulation SpectrumS. Greenberg and T. AraiProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

Vowel Height is Intimately Associated with Stress Accent in Spontaneous American English DiscourseL. Hitchcock and S. GreenbergProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

A Dutch Treatment of an Elitist Approach to Articulatory-Acoustic Feature ClassificationM. Wester, S. Greenberg, and S. ChangProceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, DenmarkSeptember 2001Speech[PDF]

Multi-Stream ASR trained with Heterogeneous Reverberant EnvironmentsM.L. ShireProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, UtahMay 2001Speech[PDF]

Global Posterior Probability Estimates as Confidence Measures in an Automatic Speech Recognition SystemW. WarrenProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2001), Salt Lake City, UtahMay 2001Speech
The Meeting Project at ICSIN. Morgan, D. Baron, J. Edwards, D. Ellis, D. Gelbart, A. Janin, T. Pfau, E. Shriberg, and A. StolckeProceedings of the Human Language Technologies Conference, San Diego, CaliforniaMarch 2001Speech[PDF]

Speech Intelligibility Derived From Asynchrounous Processing of Auditory-Visual InformationK.W. Grant and S. GreenbergProceedings of the International Conference on Auditory-Visual Speech Processing Workshop (AVSP 2001), Scheelsminde, DenmarkSeptember 2001Speech[PDF]

Pages