Automatic Speech Recognition

Real-Time End-to-End Monaural Multi-Speaker Speech Recognition Interspeech 2021 Relaxing the Conditional Independence Assumption of CTC-Based ASR by Conditioning on Intermediate Predictions Interspeech 2021 Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech EMNLP 2021 Residual Energy-Based Models for End-to-End Speech Recognition Interspeech 2021 Rethinking Evaluation in ASR: Are Our Models Robust Enough? Interspeech 2021 Revisiting Parity of Human vs. Machine Conversational Speech Transcription Interspeech 2021 Robust Continuous On-Device Personalization for Automatic Speech Recognition Interspeech 2021 ROXANNE Research Platform: Automate Criminal Investigations Interspeech 2021 SD-QA: Spoken Dialectal Question Answering for the Real World EMNLP 2021 Self-Adaptive Distillation for Multilingual Speech Recognition: Leveraging Student Independence Interspeech 2021 Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-Field Speech Recognition Interspeech 2021 Self-Supervised End-to-End ASR for Low Resource L2 Swedish Interspeech 2021 Semantic Data Augmentation for End-to-End Mandarin Speech Recognition Interspeech 2021 Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding Interspeech 2021 Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation Interspeech 2021 Sequence-Level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models Interspeech 2021 Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition Interspeech 2021 Shrinking Bigfoot: Reducing wav2vec 2.0 footprint EMNLP 2021 slimIPL: Language-Model-Free Iterative Pseudo-Labeling Interspeech 2021 Speaker Normalization Using Joint Variational Autoencoder Interspeech 2021 Speaking with a KN95 Face Mask: ASR Performance and Speaker Compensation Interspeech 2021 Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs Interspeech 2021 SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction Interspeech 2021 Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition Interspeech 2021 SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts Interspeech 2021