E-3-2: Speech Separation 2, Sound source separation |
All times are in New Zealand Time (UTC +13) |
| Presentation Time: Thursday, December 10, 15:30 - 17:15 Check your Time Zone |
| E-3-2.1: INTEGRATION OF SEMI-BLIND SPEECH SOURCE SEPARATION AND VOICE ACTIVITY DETECTION FOR FLEXIBLE SPOKEN DIALOGUE |
| Masaya Wake; Graduate School of Informatics, Kyoto University |
| Masahito Togami; LINE Corporation |
| Kazuyoshi Yoshii; Graduate School of Informatics, Kyoto University |
| Tatsuya Kawahara; Graduate School of Informatics, Kyoto University |
| E-3-2.2: DNN-BASED PERMUTATION SOLVER FOR FREQUENCY-DOMAIN INDEPENDENT COMPONENT ANALYSIS IN TWO-SOURCE MIXTURE CASE |
| Shuhei Yamaji; National Institute of Technology, Kagawa College |
| Daichi Kitamura; National Institute of Technology, Kagawa College |
| E-3-2.3: COMPUTER-RESOURCE-AWARE DEEP SPEECH SEPARATION WITH A RUN-TIME-SPECIFIED NUMBER OF BLSTM LAYERS |
| Masahito Togami; Line corporation |
| Yoshiki Masuyama; Waseda University |
| Tatsuya Komatsu; Line corporation |
| Kazuyoshi Yoshii; Kyoto University |
| Tatsuya Kawahara; Kyoto University |
| E-3-2.4: SELF-ATTENTION FOR MULTI-CHANNEL SPEECH SEPARATION IN NOISY AND REVERBERANT ENVIRONMENTS |
| Conggui Liu; Fairy Devices |
| Yoshinao Sato; Fairy Devices |
| E-3-2.5: END-TO-END MUSIC-MIXED SPEECH RECOGNITION |
| Jeongwoo Woo; Kyoto University |
| Masato Mimura; Kyoto University |
| Kazuyoshi Yoshii; Kyoto University |
| Tatsuya Kawahara; Kyoto University |
| E-3-2.6: ADAPTIVE NOISE SUPPRESSION FOR WAKE-WORD DETECTION BY TEMPORAL-DIFFERENCE GENERALIZED EIGENVALUE BEAMFORMER |
| Takehiko Kagoshima; Toshiba Corporation |
| Ning Ding; Toshiba Corporation |
| Hiroshi Fujimura; Toshiba Corporation |