Gabriel Synnaeve

A Temporal Coherence Loss Function for Learning Unsupervised Acoustic Embeddings

2016 · Procedia Computer Science

We train neural networks of varying depth with a loss function which imposes the output representations to have a temporal profile which looks like that of phonemes. We show that a simple loss function which …

Wav2Letter: an End-to-End ConvNet-based Speech Recognition System

2016 · arXiv (Cornell University)

This paper presents a simple end-to-end model for speech recognition, combining a convolutional network based acoustic model and a graph decoding. It is trained to output letters, with transcribed speech, without the need for force …

Fully Convolutional Speech Recognition

2018 · arXiv (Cornell University)

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we present an alternative approach …

Libri-Light: A Benchmark for ASR with Limited or No Supervision

2020

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 from the LibriVox project. It contains over 60K …