Technical Program
SP-P3: Acoustic Modeling II |
| Session Type: Poster |
| Time: Monday, March 6, 16:00 - 18:00 |
| Location: Churchill: Poster Area A |
| Session Chair: Liang Lu, Toyota Technological Institute at Chicago |
| SP-P3.1: PERSONALIZED ACOUSTIC MODELING BY WEAKLY SUPERVISED MULTI-TASK DEEP LEARNING USING ACOUSTIC TOKENS DISCOVERED FROM UNLABELED DATA |
| Cheng-Kuan Wei; National Taiwan University |
| Cheng-Tao Chung; National Taiwan University |
| Hung-Yi Lee; National Taiwan University |
| Lin-Shan Lee; National Taiwan University |
| SP-P3.2: UNSUPERVISED UTTERANCE-WISE BEAMFORMER ESTIMATION WITH SPEECH RECOGNITION-LEVEL CRITERION |
| Takuya Higuchi; NTT Corporation |
| Takuya Yoshioka; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Tomohiro Nakatani; NTT Corporation |
| SP-P3.3: CUMULATIVE MOVING AVERAGED BOTTLENECK SPEAKER VECTORS FOR ONLINE SPEAKER ADAPTATION OF CNN-BASED ACOUSTIC MODELS |
| Tsubasa Ochiai; NTT Corporation / Doshisha University |
| Marc Delcroix; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Atsunori Ogawa; NTT Corporation |
| Taichi Asami; NTT Corporation |
| Shigeru Katagiri; Doshisha University |
| Tomohiro Nakatani; NTT Corporation |
| SP-P3.4: UNSUPERVISED ADAPTATION FOR DEEP NEURAL NETWORKS USING ALTERNATING DIRECTION METHOD OF MULTIPLIERS |
| Roger Hsiao; Raytheon BBN Technologies |
| Tim Ng; Raytheon BBN Technologies |
| Man-Hung Siu; Raytheon BBN Technologies |
| SP-P3.5: DOMAIN ADAPTATION OF DNN ACOUSTIC MODELS USING KNOWLEDGE DISTILLATION |
| Taichi Asami; NTT Corporation |
| Ryo Masumura; NTT Corporation |
| Yoshikazu Yamaguchi; NTT Corporation |
| Hirokazu Masataki; NTT Corporation |
| Yushi Aono; NTT Corporation |
| SP-P3.6: EFFECTIVE JOINT TRAINING OF DENOISING FEATURE SPACE TRANSFORMS AND NEURAL NETWORK BASED ACOUSTIC MODELS |
| Takashi Fukuda; IBM Research - Tokyo |
| Osamu Ichikawa; IBM Research - Tokyo |
| Gakuto Kurata; IBM Research - Tokyo |
| Ryuki Tachibana; IBM Research - Tokyo |
| Samuel Thomas; IBM T.J. Watson Research Center |
| Bhuvana Ramabhadran; IBM T.J. Watson Research Center |
| SP-P3.7: HARMONIC FEATURE FUSION FOR ROBUST NEURAL NETWORK-BASED ACOUSTIC MODELING |
| Osamu Ichikawa; IBM Research - Tokyo |
| Takashi Fukuda; IBM Research - Tokyo |
| Masayuki Suzuki; IBM Research - Tokyo |
| Gakuto Kurata; IBM Research - Tokyo |
| Bhuvana Ramabhadran; IBM T.J. Watson Research Center |
| SP-P3.8: TOWARDS PHONEME INVENTORY DISCOVERY FOR DOCUMENTATION OF UNWRITTEN LANGUAGES |
| Markus Müller; Karlsruhe Institute of Technology |
| Jörg Franke; Karlsruhe Institute of Technology |
| Alex Waibel; Karlsruhe Institute of Technology |
| Sebastian Stüker; Karlsruhe Institute of Technology |
| SP-P3.9: JOINT MODELING OF ARTICULATORY AND ACOUSTIC SPACES FOR CONTINUOUS SPEECH RECOGNITION TASKS |
| Vikramjit Mitra; SRI International |
| Ganesh Sivaraman; University of Maryland |
| Chris Bartels; SRI International |
| Hosung Nam; Korea University |
| Wen Wang; SRI International |
| Carol Espy-Wilson; University of Maryland |
| Dimitra Vergyri; SRI International |
| Horacio Franco; SRI International |