Technical Program
SP-P10: Speech Recognition II |
| Session Type: Poster |
| Time: Thursday, March 24, 13:30 - 15:30 |
| Location: Poster Area H |
| Session Chair: Jasha Droppo, Microsoft Inc. |
| SP-P10.1: SYSTEM COMBINATION WITH LOG-LINEAR MODELS |
| Jingzhou Yang; University of Cambridge |
| Chao Zhang; University of Cambridge |
| Anton Ragni; University of Cambridge |
| Mark Gales; University of Cambridge |
| Philip Woodland; University of Cambridge |
| SP-P10.2: NOVEL NEURAL NETWORK BASED FUSION FOR MULTISTREAM ASR |
| Sri Harish Mallidi; Johns Hopkins University |
| Hynek Hermansky; Johns Hopkins University |
| SP-P10.3: SPEECH RECOGNITION ROBUST AGAINST SPEECH OVERLAPPING IN MONAURAL RECORDINGS OF TELEPHONE CONVERSATIONS |
| Masayuki Suzuki; IBM |
| Gakuto Kurata; IBM |
| Tohru Nagano; IBM |
| Ryuki Tachibana; IBM |
| SP-P10.4: EXPLOITING LOW-DIMENSIONAL STRUCTURES TO ENHANCE DNN BASED ACOUSTIC MODELING IN SPEECH RECOGNITION |
| Pranay Dighe; Idiap Research Instititute, École polytechnique fédérale de Lausanne |
| Gil Luyet; University of Fribourg,Idiap Research Instititute |
| Afsaneh Asaei; Idiap Research Instititute |
| Hervé Bourlard; Idiap Research Instititute, École polytechnique fédérale de Lausanne |
| SP-P10.5: A COMPARATIVE STUDY OF ROBUSTNESS OF DEEP LEARNING APPROACHES FOR VAD |
| Sibo Tong; Shanghai Jiao Tong University |
| Hao Gu; Shanghai Jiao Tong University |
| Kai Yu; Shanghai Jiao Tong University |
| SP-P10.6: IMPROVED DNN-BASED SEGMENTATION FOR MULTI-GENRE BROADCAST AUDIO |
| L. Wang; University of Cambridge |
| Chao Zhang; University of Cambridge |
| Philip Woodland; University of Cambridge |
| Mark Gales; University of Cambridge |
| Penny Karanasou; University of Cambridge |
| P. Lanchantin; University of Cambridge |
| Xunying Liu; University of Cambridge |
| Yanmin Qian; University of Cambridge |
| SP-P10.7: ON THE IMPORTANCE OF EVENT DETECTION FOR ASR |
| David Haws; IBM Thomas J. Watson Research Center |
| Dimitrios Dimitriadis; IBM Thomas J. Watson Research Center |
| George Saon; IBM Thomas J. Watson Research Center |
| Samuel Thomas; IBM Thomas J. Watson Research Center |
| Michael Picheny; IBM Thomas J. Watson Research Center |
| SP-P10.8: A PHONETICALLY AWARE SYSTEM FOR SPEECH ACTIVITY DETECTION |
| Luciana Ferrer; CONICET |
| Martin Graciarena; SRI International |
| Vikramjit Mitra; SRI International |
| SP-P10.9: FRAMEWISE SPEECH-NONSPEECH CLASSIFICATION BY NEURAL NETWORKS FOR VOICE ACTIVITY DETECTION WITH STATISTICAL NOISE SUPPRESSION |
| Yasunari Obuchi; Tokyo University of Technology |
| SP-P10.10: ROBUST SPEECH RECOGNITION FROM RATIO MASKS |
| Zhong-Qiu Wang; The Ohio State University |
| DeLiang Wang; The Ohio State University |
ICASSP 2016 Patrons
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |