2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

SPE-27: Speech Recognition 9: Confidence Measures

Session Type: Poster
Time: Wednesday, 9 June, 16:30 - 17:15
Location: Gather.Town
Session Chair: Yifan Gong, Microsoft
 
SPE-27.1: IMPROVING IDENTIFICATION OF SYSTEM-DIRECTED SPEECH UTTERANCES BY DEEP LEARNING OF ASR-BASED WORD EMBEDDINGS AND CONFIDENCE METRICS
         Vilayphone Vilaysouk; Mila, Université de Montréal
         Amr Nour-Eldin; Nuance Communications
         Dermot Connolly; Nuance Communications
 
SPE-27.2: BLSTM-BASED CONFIDENCE ESTIMATION FOR END-TO-END SPEECH RECOGNITION
         Atsunori Ogawa; NTT Corporation
         Naohiro Tawara; NTT Corporation
         Takatomo Kano; NTT Corporation
         Marc Delcroix; NTT Corporation
 
SPE-27.3: CONFIDENCE ESTIMATION FOR ATTENTION-BASED SEQUENCE-TO-SEQUENCE MODELS FOR SPEECH RECOGNITION
         Qiujia Li; University of Cambridge
         David Qiu; Google LLC
         Yu Zhang; Google LLC
         Bo Li; Google LLC
         Yanzhang He; Google LLC
         Phil Woodland; University of Cambridge
         Liangliang Cao; Google LLC
         Trevor Strohman; Google LLC
 
SPE-27.4: LEARNING WORD-LEVEL CONFIDENCE FOR SUBWORD END-TO-END ASR
         David Qiu; Google
         Qiujia Li; University of Cambridge
         Yanzhang He; Google
         Yu Zhang; Google
         Bo Li; Google
         Liangliang Cao; Google
         Rohit Prabhavalkar; Google
         Deepti Bhatia; Google
         Wei Li; Google
         Ke Hu; Google
         Tara N. Sainath; Google
         Ian McGraw; Google
 
SPE-27.5: NEURAL UTTERANCE CONFIDENCE MEASURE FOR RNN-TRANSDUCERS AND TWO PASS MODELS
         Ashutosh Gupta; Samsung Research Institute, Bangelore
         Ankur Kumar; Samsung Research Institute, Bangelore
         Dhananjaya Gowda; Samsung Research Korea
         Kwangyoun Kim; Samsung Research Korea
         Sachin Singh; Samsung Bangalore
         Shatrughan Singh; Samsung Research
         Chanwoo Kim; Samsung Korea
 
SPE-27.6: DETECTING ADVERSARIAL ATTACKS ON AUDIOVISUAL SPEECH RECOGNITION
         Pingchuan Ma; Imperial College London
         Petridis Stavros; Imperial College London
         Maja Pantic; Imperial College London