Search/decoding techniques and confidence measures for ASR

LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring
(3 minutes introduction)

Anton Mitrofanov (ITMO University, Russia), Mariya Korenevskaya (STC-innovations, Russia), Ivan Podluzhny (ITMO University, Russia), Yuri Khokhlov (STC-innovations, Russia), Aleksandr Laptev (ITMO University, Russia), Andrei Andrusenko (ITMO University, Russia), Aleksei Ilin (STC-innovations, Russia), Maxim Korenevsky (STC-innovations, Russia), Ivan Medennikov (ITMO University, Russia), Aleksei Romanenko (ITMO University, Russia)

Deep neural network calibration for E2E speech recognition system
(3 minutes introduction)

Mun-Hak Lee (Hanyang University, Korea), Joon-Hyuk Chang (Hanyang University, Korea)

Deep neural network calibration for E2E speech recognition system
(longer introduction)

Mun-Hak Lee (Hanyang University, Korea), Joon-Hyuk Chang (Hanyang University, Korea)

Residual Energy-Based Models for End-to-End Speech Recognition
(3 minutes introduction)

Qiujia Li (University of Cambridge, UK), Yu Zhang (Google, USA), Bo Li (Google, USA), Liangliang Cao (Google, USA), Philip C. Woodland (University of Cambridge, UK)

Insights on Neural Representations for End-to-End Speech Recognition
(3 minutes introduction)

Anna Ollerenshaw (University of Sheffield, UK), Md. Asif Jalal (University of Sheffield, UK), Thomas Hain (University of Sheffield, UK)

Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models
(3 minutes introduction)

Amber Afshan (University of California at Los Angeles, USA), Kshitiz Kumar (Microsoft, USA), Jian Wu (Microsoft, USA)

InterSpeech 2021