SPE-18.1
LATTICE RESCORING BASED ON LARGE ENSEMBLE OF COMPLEMENTARY NEURAL LANGUAGE MODELS
Atsunori Ogawa, Naohiro Tawara, Marc Delcroix, Shoko Araki, NTT Corporation, Japan
Session:
Speech Recognition: General Topics I
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Mon, 9 May, 20:00 - 20:45 China Time (UTC +8)
Mon, 9 May, 12:00 - 12:45 UTC
Mon, 9 May, 12:00 - 12:45 UTC
Session Chair:
Torbjørn Svendsen,
Session SPE-18
SPE-18.1: LATTICE RESCORING BASED ON LARGE ENSEMBLE OF COMPLEMENTARY NEURAL LANGUAGE MODELS
Atsunori Ogawa, Naohiro Tawara, Marc Delcroix, Shoko Araki, NTT Corporation, Japan
SPE-18.2: Continual learning using lattice-free MMI for speech recognition
Hossein Hadian, Arseniy Gorin, Behavox, Canada
SPE-18.3: NON-AUTOREGRESSIVE TRANSFORMER WITH UNIFIED BIDIRECTIONAL DECODER FOR AUTOMATIC SPEECH RECOGNITION
Chuan-Fei Zhang, Yan Liu, Tian-Hao Zhang, Song-Lu Chen, Xu-Cheng Yin, University of Science and Technology Beijing, China; Feng Chen, EEasy Technology Company Ltd., China
SPE-18.4: MODEL-BASED APPROACH FOR MEASURING THE FAIRNESS IN ASR
Zhe Liu, Irina-Elena Veliche, Fuchun Peng, Meta Platforms, Inc, United States of America
SPE-18.5: IMPROVING CONFIDENCE ESTIMATION ON OUT-OF-DOMAIN DATA FOR END-TO-END SPEECH RECOGNITION
Qiujia Li, Phil Woodland, University of Cambridge, United Kingdom of Great Britain and Northern Ireland; Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Google LLC, United States of America
SPE-18.6: Parallel Composition of Weighted Finite-State Transducers
Shubho Sengupta, Vineel Pratap, Facebook, United States of America; Awni Hannun, Zoom, United States of America