SPE-10.6
Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition
Chao-Han Huck Yang, Georgia Institute of Technology, United States of America; Zeeshan Ahmed, Yile Gu, Joseph Szurley, Roger Ren, Linda Liu, Andreas Stolcke, Ivan Bulyko, Amazon, United States of America
Session:
Speech Recognition: Robust Speech Recognition II
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Sun, 8 May, 22:00 - 22:45 China Time (UTC +8)
Sun, 8 May, 14:00 - 14:45 UTC
Sun, 8 May, 14:00 - 14:45 UTC
Session Chair:
Giampiero Salvi, NTNU
Session SPE-10
SPE-10.1: A TIME DOMAIN PROGRESSIVE LEARNING APPROACH WITH SNR CONSTRICTION FOR SINGLE-CHANNEL SPEECH ENHANCEMENT AND RECOGNITION
Zhaoxu Nian, Jun Du, University of Science and Technology of China, China; Yu Ting Yeung, Renyu Wang, Huawei Noah’s Ark Lab, China
SPE-10.2: A TWO-STEP APPROACH TO LEVERAGE CONTEXTUAL DATA: SPEECH RECOGNITION IN AIR-TRAFFIC COMMUNICATION
Iuliia Nigmatulina, Juan Zuluaga-Gomez, Amrutha Prasad, Seyyed Saeed Sarfjoo, Petr Motlicek, Idiap Research Institute, Switzerland
SPE-10.3: LEARNING TO ENHANCE OR NOT: NEURAL NETWORK-BASED SWITCHING OF ENHANCED AND OBSERVED SIGNALS FOR OVERLAPPING SPEECH RECOGNITION
Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Naoyuki Kamo, Takafumi Moriya, NTT Corporation, Japan
SPE-10.4: INTERACTIVE FEATURE FUSION FOR END-TO-END NOISE-ROBUST SPEECH RECOGNITION
Yuchen Hu, Nana Hou, Chen Chen, Eng Siong Chng, Nanyang Technological University, Singapore
SPE-10.5: SPEAKER REINFORCEMENT USING TARGET SOURCE EXTRACTION FOR ROBUST AUTOMATIC SPEECH RECOGNITION
Catalin Zorila, Rama Doddipatla, Toshiba Cambridge Research Laboratory, United Kingdom of Great Britain and Northern Ireland
SPE-10.6: Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition
Chao-Han Huck Yang, Georgia Institute of Technology, United States of America; Zeeshan Ahmed, Yile Gu, Joseph Szurley, Roger Ren, Linda Liu, Andreas Stolcke, Ivan Bulyko, Amazon, United States of America