arXiv (Cornell University) · 2021 · 43 citations · 28 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingDeep LearningMultilingual Natural Language ProcessingMultimodal CorporaSpeech RecognitionSpoken CorporaAutomatic RecognitionAutoregressive ModelsConnectionist Temporal ClassificationEnd-to-end Speech RecognitionMultilingual Speech RecognitionTemporal Convolutional Networks
We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best autoregressive Transducer models.
28
Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 12.5K citations
Librispeech: An ASR corpus based on public domain audio books
Vassil Panayotov, Guoguo Chen, Daniel Povey et al. · 2015 · 6K citations
Computing, Computer Science, English +17
Connectionist temporal classification
Alex Graves, Santiago Fernández, Faustino Gomez et al. · 2006 · 5.4K citations
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Daniel Park, William Chan, Yu Zhang et al. · 2019 · 3.5K citations · Full text
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Thomas Wolf, Lysandre Debut, Victor Sanh et al. · arXiv (Cornell University) · 2019 · 3.1K citations · Full text