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

Code

• github.com/mailong25/vietnamese-speech-recognition
  pytorch★ 379
• github.com/ashwin9999/Capstone-Speech-to-SQL
  tf★ 0
• github.com/silversparro/wav2letter.pytorch
  pytorch★ 0
• github.com/MrMao/wav2letter
  torch★ 0
• github.com/ashwin9999/speech-recognition-CNN
  tf★ 0
• github.com/CorrelAid/codingchallenge1020_team1
  tf★ 0
• github.com/JuliusKunze/speechless
  tf★ 0
• github.com/eric-erki/wav2letter
  torch★ 0

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.

Tasks

Reproductions