Home Call for Papers Paper Submission Exhibits Support Opportunities Dallas Information Social Events Technical Program Paper Search Plenary Talks Registration Housing Tutorials Special Sessions Show and Tell Workshops THEMES 2010 Registration Spoken Language Processing Grant Organizing Committee Technical Program CommitteeSP-L7: Acoustic Modeling I |
| Session Type: Lecture |
| Time: Thursday, March 18, 13:30 - 15:30 |
| Location: Room B |
| Session Chair: Dirk Van Compernolle, K. Univ Leuven, Belgium |
| SP-L7.1: COVARIANCE CLUSTERING ON RIEMANNIAN MANIFOLDS FOR ACOUSTIC MODEL COMPRESSION |
| Yusuke Shinohara; Toshiba Corporation |
| Takashi Masuko; Toshiba Corporation |
| Masami Akamine; Toshiba Corporation |
| SP-L7.2: SUBSPACE GAUSSIAN MIXTURE MODELS FOR SPEECH RECOGNITION |
| Daniel Povey; Microsoft |
| Lukas Burget; Brno University of Technology |
| Mohit Agarwal; Indian Institute of Information Technology, Allahabad |
| Pinar Akyazi; Boğaziçi University |
| Kai Feng; Hong Kong University of Science and Technology |
| Arnab Ghoshal; Saarland University |
| Ondrej Glembek; Brno University of Technology |
| Nagendra Goel; Go-Vivace Inc. |
| Martin Karafiat; Brno University of Technology |
| Ariya Rastrow; Johns Hopkins University |
| Richard Rose; McGill University |
| Petr Schwarz; Brno University of Technology |
| Samuel Thomas; Johns Hopkins University |
| SP-L7.3: MULTILINGUAL ACOUSTIC MODELING FOR SPEECH RECOGNITION BASED ON SUBSPACE GAUSSIAN MIXTURE MODELS |
| Lukas Burget; Brno University of Technology |
| Petr Schwarz; Brno University of Technology |
| Mohit Agarwal; Indian Institute of Information Technology, Allahabad |
| Pinar Akyazi; Boğaziçi University |
| Kai Feng; Hong Kong University of Science and Technology |
| Arnab Ghoshal; Saarland University |
| Ondrej Glembek; Brno University of Technology |
| Nagendra Goel; Go-Vivace Inc. |
| Martin Karafiat; Brno University of Technology |
| Daniel Povey; Microsoft |
| Ariya Rastrow; Johns Hopkins University |
| Richard Rose; McGill University |
| Samuel Thomas; Johns Hopkins University |
| SP-L7.4: DISCRIMINATIVE TEMPLATE EXTRACTION FOR DIRECT MODELING |
| Shankar Shivappa; University of California, San Diego |
| Patrick Nguyen; Microsoft Research |
| Geoffrey Zweig; Microsoft Research |
| SP-L7.5: SELECTING STATIC AND DYNAMIC FEATURES USING AN ADVANCED AUDITORY MODEL FOR SPEECH RECOGNITION |
| Christos Koniaris; KTH - Royal Institute of Technology |
| Saikat Chatterjee; KTH - Royal Institute of Technology |
| W. Bastiaan Kleijn; KTH - Royal Institute of Technology |
| SP-L7.6: SPARSE CODING FOR SPEECH RECOGNITION |
| Sivaram Garimella; Johns Hopkins University |
| Sridhar Krishna Nemala; Johns Hopkins University |
| Mounya Elhilali; Johns Hopkins University |
| Trac D. Tran; Johns Hopkins University |
| Hynek Hermansky; Johns Hopkins University |
©2015 Conference Management Services, Inc. 
email: webmaster@icassp2010.com Last updated Tuesday, January 12, 2010
