UPDF AI
New Chat
Search History
Scholar ResearchPaper SearchLibrary
Chats
UPDF AI

Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

Samuel Kriman,Stanislav Beliaev,6 Authors,Yang Zhang

2019 · DOI: 10.1109/ICASSP40776.2020.9053889
IEEE International Conference on Acoustics, Speech, and Signal Processing · 307 Citations

TLDR

A new end-to-end neural acoustic model for automatic speech recognition that achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models.

Abstract

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.