Reducing exposure bias in training recurrent neural network transducersXiaodong CuiBrian Kingsburyet al.2021INTERSPEECH 2021
Token-level supervised contrastive learning for punctuation restorationQiushi HuangTom Koet al.2021INTERSPEECH 2021
Mucs 2021: Multilingual and code-switching asr challenges for low resource indian languagesAnuj DiwanRakesh Vaideeswaranet al.2021INTERSPEECH 2021
Integrating dialog history into end-to-end spoken language understanding systemsJatin GanhotraSamuel Thomaset al.2021INTERSPEECH 2021
Synthesis of expressive speaking styles with limited training data in a multi-speaker, prosody-controllable sequence-to-sequence architectureSlava ShechtmanRaul Fernandezet al.2021INTERSPEECH 2021
Knowledge distillation based training of universal ASR source models for cross-lingual transferTakashi FukudaSamuel Thomas2021INTERSPEECH 2021