Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
Machine Learning
2016-09-14 v2 Artificial Intelligence
Computation and Language
Abstract
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 alignment of phonemes. We introduce an automatic segmentation criterion for training from sequence annotation without alignment that is on par with CTC while being simpler. We show competitive results in word error rate on the Librispeech corpus with MFCC features, and promising results from raw waveform.
Cite
@article{arxiv.1609.03193,
title = {Wav2Letter: an End-to-End ConvNet-based Speech Recognition System},
author = {Ronan Collobert and Christian Puhrsch and Gabriel Synnaeve},
journal= {arXiv preprint arXiv:1609.03193},
year = {2016}
}
Comments
8 pages, 4 figures (7 plots/schemas), 2 tables (4 tabulars)