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

2016/09/11 by Ronan Collobert, Christian Puhrsch, Collobert, Ronan +3 · 7 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.6 #I.2.7 #Machine Learning (cs.LG) #Music and Audio Processing #Natural Language Processing Techniques #Speech Recognition and Synthesis #cs.AI #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.1609.03193

8 pages, 4 figures (7 plots/schemas), 2 tables (4 tabulars)

openalex publication_date 2016/09/11 · arxiv created 2016/09/13 · arxiv updated 2016/09/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Very Deep Multilingual Convolutional Neural Networks for LVCSR

Cited by

• Learning Robust and Multilingual Speech Representations
• Why does CTC result in peaky behavior?
• Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models
• Automatic Grammar Augmentation for Robust Voice Command Recognition
• Multimodal Machine Learning: A Survey and Taxonomy
• Letter-Based Speech Recognition with Gated ConvNets
• Simplified End-to-End MMI Training and Voting for ASR

Related

• Letter-Based Speech Recognition with Gated ConvNets
• Fully Convolutional Speech Recognition
• wav2vec: Unsupervised Pre-training for Speech Recognition
• Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data
• Unsupervised Speech Recognition