SLP-P5: End-to-end Speech Recognition III: Source Integration and Knowledge Transfer |
| Session Type: Poster |
| Time: Wednesday, May 15, 08:30 - 10:30 |
| Location: Poster Area A, Ground Floor |
| Session Chair: Tatsuya Kawahara, Kyoto University
|
| |
| SLP-P5.1: SEQUENCE-LEVEL KNOWLEDGE DISTILLATION FOR MODEL COMPRESSION OF ATTENTION-BASED SEQUENCE-TO-SEQUENCE SPEECH RECOGNITION |
| Raden Mu'az Mun'im; Tokyo Institute of Technology |
| Nakamasa Inoue; Tokyo Institute of Technology |
| Koichi Shinoda; Tokyo Institute of Technology |
| |
| SLP-P5.2: INVESTIGATION OF SEQUENCE-LEVEL KNOWLEDGE DISTILLATION METHODS FOR CTC ACOUSTIC MODELS |
| Ryoichi Takashima; National Institute of Information and Communications Technology |
| Sheng Li; National Institute of Information and Communications Technology |
| Hisashi Kawai; National Institute of Information and Communications Technology |
| |
| SLP-P5.3: MULTI-SPEAKER SEQUENCE-TO-SEQUENCE SPEECH SYNTHESIS FOR DATA AUGMENTATION IN ACOUSTIC-TO-WORD SPEECH RECOGNITION |
| Sei Ueno; Kyoto University |
| Masato Mimura; Kyoto University |
| Shinsuke Sakai; Kyoto University |
| Tatsuya Kawahara; Kyoto University |
| |
| SLP-P5.4: SEMI-SUPERVISED END-TO-END SPEECH RECOGNITION USING TEXT-TO-SPEECH AND AUTOENCODERS |
| Shigeki Karita; NTT Communication Science Laboratories |
| Shinji Watanabe; Johns Hopkins University |
| Tomoharu Iwata; NTT Communication Science Laboratories |
| Marc Delcroix; NTT Communication Science Laboratories |
| Atsunori Ogawa; NTT Communication Science Laboratories |
| Tomohiro Nakatani; NTT Communication Science Laboratories |
| |
| SLP-P5.5: PHOEBE: PRONUNCIATION-AWARE CONTEXTUALIZATION FOR END-TO-END SPEECH RECOGNITION |
| Antoine Bruguier; Google, Inc. |
| Rohit Prabhavalkar; Google, Inc. |
| Golan Pundak; Google, Inc. |
| Tara N. Sainath; Google, Inc. |
| |
| SLP-P5.6: ADVERSARIAL TRAINING OF END-TO-END SPEECH RECOGNITION USING A CRITICIZING LANGUAGE MODEL |
| Alexander H. Liu; National Taiwan University |
| Hung-yi Lee; National Taiwan University |
| Lin-shan Lee; National Taiwan University |
| |
| SLP-P5.7: KNOWLEDGE DISTILLATION USING OUTPUT ERRORS FOR SELF-ATTENTION END-TO-END MODELS |
| Ho-Gyeong Kim; Samsung Advanced Institute of Technology, Samsung Electronics |
| Hwidong Na; Samsung Advanced Institute of Technology, Samsung Electronics |
| Hoshik Lee; Samsung Advanced Institute of Technology, Samsung Electronics |
| Jihyun Lee; Samsung Advanced Institute of Technology, Samsung Electronics |
| Tae Gyoon Kang; Samsung Advanced Institute of Technology, Samsung Electronics |
| Min-Joong Lee; Samsung Advanced Institute of Technology, Samsung Electronics |
| Young Sang Choi; Samsung Advanced Institute of Technology, Samsung Electronics |
| |
| SLP-P5.8: END-TO-END CONTEXTUAL SPEECH RECOGNITION USING CLASS LANGUAGE MODELS AND A TOKEN PASSING DECODER |
| Zhehuai Chen; Shanghai Jiao Tong University |
| Mahaveer Jain; Facebook |
| Yongqiang Wang; Facebook |
| Michael Seltzer; Facebook |
| Christian Fuegen; Facebook |
| |
| SLP-P5.9: LANGUAGE MODEL INTEGRATION BASED ON MEMORY CONTROL FOR SEQUENCE TO SEQUENCE SPEECH RECOGNITION |
| Jaejin Cho; Johns Hopkins University |
| Shinji Watanabe; Johns Hopkins University |
| Takaaki Hori; Mitsubishi Electric Research Laboratories |
| Murali Karthick Baskar; Brno University of Technology |
| Hirofumi Inaguma; Kyoto University |
| Jesús Villalba; Johns Hopkins University |
| Najim Dehak; Johns Hopkins University |
| |