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

HLT-5: Language Understanding 1: End-to-end Speech Understanding 1

Session Type: Poster
Time: Wednesday, 9 June, 13:00 - 13:45
Location: Gather.Town
Session Chair: Jasha Droppo, Amazon
 
HLT-5.1: END2END ACOUSTIC TO SEMANTIC TRANSDUCTION
         Valentin Pelloin; LIUM - Le Mans Université
         Nathalie Camelin; LIUM - Le Mans Université
         Antoine Laurent; LIUM - Le Mans Université
         Renato De Mori; LIA - Université d'Avignon
         Antoine Caubrière; LIUM - Le Mans Université
         Yannick Estève; LIA - Université d'Avignon
         Sylvain Meignier; LIUM - Le Mans Université
 
HLT-5.2: ACOUSTICS BASED INTENT RECOGNITION USING DISCOVERED PHONETIC UNITS FOR LOW RESOURCE LANGUAGES
         Akshat Gupta; Carnegie Mellon University
         Xinjian Li; Carnegie Mellon University
         SaiKrishna Rallabandi; Carnegie Mellon University
         Alan Black; Carnegie Mellon University
 
HLT-5.3: SPEECH-LANGUAGE PRE-TRAINING FOR END-TO-END SPOKEN LANGUAGE UNDERSTANDING
         Yao Qian; Microsoft Cognitive Services Research Group
         Ximo Bian; Beijing Institute of Technology
         Yu Shi; Microsoft Cognitive Services Research Group
         Naoyuki Kanda; Microsoft Cognitive Services Research Group
         Leo Shen; Microsoft Cognitive Services Research Group
         Zhen Xiao; Microsoft Cognitive Services Research Group
         Michael Zeng; Microsoft Cognitive Services Research Group
 
HLT-5.4: TWO-STAGE TEXTUAL KNOWLEDGE DISTILLATION FOR END-TO-END SPOKEN LANGUAGE UNDERSTANDING
         Seongbin Kim; Inha University
         Gyuwan Kim; NAVER Corp.
         Seongjin Shin; NAVER Corp.
         Sangmin Lee; Inha University
 
HLT-5.5: SEMI-SUPERVISED SPOKEN LANGUAGE UNDERSTANDING VIA SELF-SUPERVISED SPEECH AND LANGUAGE MODEL PRETRAINING
         Cheng-I Lai; Massachusetts Institute of Technology
         Yung-Sung Chuang; National Taiwan University
         Hung-Yi Lee; National Taiwan University
         Shang-Wen Li; Amazon Inc.
         James Glass; Massachusetts Institute of Technology
 
HLT-5.6: DO AS I MEAN, NOT AS I SAY: SEQUENCE LOSS TRAINING FOR SPOKEN LANGUAGE UNDERSTANDING
         Milind Rao; Amazon Alexa
         Pranav Dheram; Amazon Alexa
         Gautam Tiwari; Amazon Alexa
         Anirudh Raju; Amazon Alexa
         Jasha Droppo; Amazon Alexa
         Ariya Rastrow; Amazon Alexa
         Andreas Stolcke; Amazon Alexa