2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-39: Speech Recognition 13: Acoustic Modeling 1 |
| Session Type: Poster |
| Time: Thursday, 10 June, 15:30 - 16:15 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Xiaodong Cui, IBM |
| SPE-39.1: SPEECH ACOUSTIC MODELLING FROM RAW PHASE SPECTRUM |
| Erfan Loweimi; University of Edinburgh |
| Zoran Cvetkovic; King's College London |
| Peter Bell; University of Edinburgh |
| Steve Renals; University of Edinburgh |
| SPE-39.2: AN INVESTIGATION OF USING HYBRID MODELING UNITS FOR IMPROVING END-TO-END SPEECH RECOGNITION SYSTEM |
| Shunfei Chen; Hithink RoyalFlush AI Research Institute |
| Xinhui Hu; Hithink RoyalFlush AI Research Institute |
| Sheng Li; National Institute of Information and Communications Technology |
| Xinkang Xu; Hithink RoyalFlush AI Research Institute |
| SPE-39.3: FEDERATED ACOUSTIC MODELING FOR AUTOMATIC SPEECH RECOGNITION |
| Xiaodong Cui; IBM T. J. Watson Research Center |
| Songtao Lu; IBM T. J. Watson Research Center |
| Brian Kingsbury; IBM T. J. Watson Research Center |
| SPE-39.4: EAT: ENHANCED ASR-TTS FOR SELF-SUPERVISED SPEECH RECOGNITION |
| Murali Karthick Baskar; Brno University of Technology |
| Lukáš Burget; Brno University of Technology |
| Shinji Watanabe; Johns Hopkins University |
| Ramon Astudillo; IBM T. J. Watson Research Center |
| Jan "Honza" Cernocky; Brno University of Technology |
| SPE-39.5: NEURAL ARCHITECTURE SEARCH FOR LF-MMI TRAINED TIME DELAY NEURAL NETWORKS |
| Shoukang Hu; The Chinese University of Hong Kong |
| Xurong Xie; The Chinese University of Hong Kong |
| Shansong Liu; The Chinese University of Hong Kong |
| Mingyu Cui; The Chinese University of Hong Kong |
| Mengzhe Geng; The Chinese University of Hong Kong |
| Xunying Liu; The Chinese University of Hong Kong |
| Helen Meng; The Chinese University of Hong Kong |
| SPE-39.6: HYPOTHESIS STITCHER FOR END-TO-END SPEAKER-ATTRIBUTED ASR ON LONG-FORM MULTI-TALKER RECORDINGS |
| Xuankai Chang; Johns Hopkins University |
| Naoyuki Kanda; Microsoft Corporation |
| Yashesh Gaur; Microsoft Corporation |
| Xiaofei Wang; Microsoft Corporation |
| Zhong Meng; Microsoft Corporation |
| Takuya Yoshioka; Microsoft Corporation |