2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-27: Speech Recognition 9: Confidence Measures |
| Session Type: Poster |
| Time: Wednesday, 9 June, 16:30 - 17:15 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| 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 |