5.2k citations · 8.2k across the 49 of their papers we have counts for
7 papers · 2 filters
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Jacob Kahn, Morgane Rivière, Weiyi Zheng +12
We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books f…
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
Gabriel Synnaeve, Qiantong Xu, Jacob Kahn +6
We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functio…
Word-level Speech Recognition with a Letter to Word Encoder
Ronan Collobert, Awni Hannun, Gabriel Synnaeve
We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence mo…
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
Awni Hannun, Ann Lee, Qiantong Xu +1
We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnit…
wav2vec: Unsupervised Pre-training for Speech Recognition
Steffen Schneider, Alexei Baevski, Ronan Collobert +1
We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting…
Who Needs Words? Lexicon-Free Speech Recognition
Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
Lexicon-free speech recognition naturally deals with the problem of out-of-vocabulary (OOV) words. In this paper, we show that character-based language models (LM) can perform as w…
A Fully Differentiable Beam Search Decoder
Ronan Collobert, Awni Hannun, Gabriel Synnaeve
We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combi…