T
T. J. Tsai
Researcher at University of California, Berkeley
Publications - 13
Citations - 130
T. J. Tsai is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Modality (human–computer interaction). The author has an hindex of 6, co-authored 10 publications receiving 114 citations. Previous affiliations of T. J. Tsai include Microsoft.
Papers
More filters
Proceedings ArticleDOI
All for One: Feature Combination for Highly Channel-Degraded Speech Activity Detection
Martin Graciarena,Abeer Alwan,Daniel P. W. Ellis,Horacio Franco,Luciana Ferrer,John H. L. Hansen,Adam Janin,Byungsuk Lee,Yun Lei,Vikramjit Mitra,Nelson Morgan,Seyed Omid Sadjadi,T. J. Tsai,Nicolas Scheffer,Lee Ngee Tan,Benjamin Williams +15 more
TL;DR: This paper presents a feature combination approach to improve SAD on highly channel degraded speech as part of the Defense Advanced Research Projects Agency’s (DARPA) Robust Automatic Transcription of Speech (RATS) program and presents single, pairwise and all feature combinations.
Journal ArticleDOI
A Study of Multimodal Addressee Detection in Human-Human-Computer Interaction
TL;DR: It is suggested that acoustic, lexical, and system-state information is an effective and practical combination of modalities to use for addressee detection in multiparty, open-world dialogue systems in which the agent plays an active, conversational role.
Proceedings ArticleDOI
Are you TED talk material? comparing prosody in professors and TED speakers.
TL;DR: The aim is to identify the characteristics that separate TED speakers from other public speakers, and to investigate which features are most discriminative, and discuss conflating factors that might contribute to those features.
Proceedings ArticleDOI
Longer Features: They do a speech detector good.
T. J. Tsai,Nelson Morgan +1 more
TL;DR: Compared to the other backends, Adaboost with tree stumps performed particularly well with Gabor features and particularly poorly with MFCCs, and an investigation into the reasons for this disparity suggests that the most useful features for SAD incorporate information over longer time scales.
Proceedings ArticleDOI
Multimodal addressee detection in multiparty dialogue systems
TL;DR: This study suggests that acoustic, lexical, and system state information are an effective, economical combination of modalities to use in addressee detection.