SLP-P12.2
CAN WE TRUST EXPLAINABLE AI METHODS ON ASR? AN EVALUATION ON PHONEME RECOGNITION
Xiaoliang Wu, Peter Bell, Ajitha Rajan, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland
Session:
SLP-P12: Robust speech recognition and adaptation I Poster
Track:
Speech and Language Processing
Location:
Poster Zone 1A
Poster Board PZ-1A.2
Poster Board PZ-1A.2
Presentation Time:
Wed, 17 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Masakiyo Fujimoto, NICT
Session SLP-P12
SLP-P12.1: A STUDY ON THE ADVERSE IMPACT OF SYNTHETIC SPEECH ON SPEECH RECOGNITION
Jian Huang, Yancheng Bai, Yang Cai, Wei Bian, Alibaba Group, China
SLP-P12.2: CAN WE TRUST EXPLAINABLE AI METHODS ON ASR? AN EVALUATION ON PHONEME RECOGNITION
Xiaoliang Wu, Peter Bell, Ajitha Rajan, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland
SLP-P12.3: UNSUPERVISED MULTI-DOMAIN DATA SELECTION FOR ASR FINE-TUNING
Nikolaos Lagos, Ioan Calapodescu, Naver Labs, France
SLP-P12.5: TEXT-ONLY UNSUPERVISED DOMAIN ADAPTATION FOR NEURAL TRANSDUCER-BASED ASR PERSONALIZATION USING SYNTHESIZED DATA
Dong-Hyun Kim, Jae-Hong Lee, Joon-Hyuk Chang, Hanyang University, Korea, Republic of
SLP-P12.6: T-SOT FNT: STREAMING MULTI-TALKER ASR WITH TEXT-ONLY DOMAIN ADAPTATION CAPABILITY
Jian Wu, Naoyuki Kanda, Takuya Yoshioka, Rui Zhao, Zhuo Chen, Jinyu Li, Microsoft, United States of America
SLP-P12.7: FASTINJECT: INJECTING UNPAIRED TEXT DATA INTO CTC-BASED ASR TRAINING
Keqi Deng, Philip Woodland, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
SLP-P12.8: STATEFUL CONFORMER WITH CACHE-BASED INFERENCE FOR STREAMING AUTOMATIC SPEECH RECOGNITION
Vahid Noroozi, Somshubra Majumdar, NVIDIA, United States of America; Ankur Kumar, UCLA, United States of America; Jagadeesh Balem, Boris Ginsburg, NVIDIA, United States of America
SLP-P12.9: AUTOMATIC SPEECH RECOGNITION TUNED FOR CHILD SPEECH IN THE CLASSROOM
Rosy Southwell, Wayne Ward, University of Colorado Boulder, United States of America; Viet Anh Trinh, Worcester Polytechnic Institute, United States of America; Charis Clevenger, Clay Clevenger, Emily Watts, Jason Reitman, Sidney D'Mello, University of Colorado Boulder, United States of America; Jacob Whitehill, Worcester Polytechnic Institute, United States of America
SLP-P12.10: IMPROVING SPEECH RECOGNITION FOR AFRICAN AMERICAN ENGLISH WITH AUDIO CLASSIFICATION
Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Alëna Aksënova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Google LLC, United States of America; Zion Mengesha, Google LLC, Stanford University, United States of America; Dongseong Hwang, Tara Sainath, Françoise Beaufays, Pedro Moreno Mengibar, Google LLC, United States of America
SLP-P12.11: CONTEXTUAL BIASING METHODS FOR IMPROVING RARE WORD DETECTION IN AUTOMATIC SPEECH RECOGNITION
Mrinmoy Bhattacharjee, Iuliia Nigmatulina, Amrutha Prasad, Pradeep Rangappa, Srikanth Madikeri, Petr Motlicek, Idiap Research Institute, Switzerland; Hartmut Helmke, Matthias Kleinert, German Aerospace Center (DLR), Germany
SLP-P12.12: Monte Carlo Self-Training For Speech Recognition
Anshuman Tripathi, Soheil Khorram, Han Lu, Jaeyoung Kim, Qian Zhang, Hasim Sak, Google, United States of America
Contacts