Technical Program
SP-L3: Robust Speech Recognition |
| Session Type: Lecture |
| Time: Tuesday, March 7, 08:30 - 10:30 |
| Location: Grand Salon 16 |
| Session Chairs: Shinji Watanabe, MERL and Rick Rose, Google |
| SP-L3.1: IMPROVED CEPSTRA MINIMUM-MEAN-SQUARE-ERROR NOISE REDUCTION ALGORITHM FOR ROBUST SPEECH RECOGNITION |
| Jinyu Li; Microsoft |
| Yan Huang; Microsoft |
| Yifan Gong; Microsoft |
| SP-L3.2: COMBINATION STRATEGY BASED ON RELATIVE PERFORMANCE MONITORING FOR MULTI-STREAM REVERBERANT SPEECH RECOGNITION |
| Feifei Xiong; Fraunhofer IDMT/HSA |
| Stefan Goetze; Fraunhofer IDMT/HSA |
| Bernd T. Meyer; Johns Hopkins University |
| SP-L3.3: ONLINE ENVIRONMENTAL ADAPTATION OF CNN-BASED ACOUSTIC MODELS USING SPATIAL DIFFUSENESS FEATURES |
| Christian Huemmer; NTT Corporation |
| Marc Delcroix; NTT Corporation |
| Atsunori Ogawa; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Tomohiro Nakatani; NTT Corporation |
| Walter Kellermann; FAU Erlangen-Nuremberg |
| SP-L3.4: A NETWORK OF DEEP NEURAL NETWORKS FOR DISTANT SPEECH RECOGNITION |
| Mirco Ravanelli; Fondazione Bruno Kessler |
| Philemon Brakel; University of Montreal |
| Maurizio Omologo; Fondazione Bruno Kessler |
| Yoshua Bengio; University of Montreal |
| SP-L3.5: DISCRIMINATIVE IMPORTANCE WEIGHTING OF AUGMENTED TRAINING DATA FOR ACOUSTIC MODEL TRAINING |
| Sunit Sivasankaran; INRIA-Nancy |
| Emmanuel Vincent; INRIA-Nancy |
| Irina Illina; INRIA-Nancy |
| SP-L3.6: UNSUPERVISED SPEAKER ADAPTATION OF BATCH NORMALIZED ACOUSTIC MODELS FOR ROBUST ASR |
| Zhong-Qiu Wang; The Ohio State University |
| DeLiang Wang; The Ohio State University |