State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention with Dilated 1D Convolutions

By Kyu J. Han, Ramon Prieto, Kaixing(Kai) Wu, Tao Ma. 2019

79 citations recorded by the source corpus.

Self-attention has been a huge success for many downstream tasks in NLP, which led to exploration of applying self-attention to speech problems as well. The efficacy of self-attention in speech applications, however, seems not fully blown yet since it is challenging to handle highly correlated speech frames in the context of self-attention. In this paper we propose a new neural network model architecture, namely multi-stream self-attention, to address the issue thus make the self-attention mechanism more effective for speech recognition. The proposed model architecture consists of parallel streams of self-attention encoders, and each stream has layers of 1D convolutions with dilated kernels whose dilation rates are unique given stream, followed by a self-attention layer. The self-attention mechanism in each stream pays attention to only one resolution of input speech frames and the attentive computation can be more efficient. In a later stage, outputs from all the streams are concatenated then linearly projected to the final embedding. By stacking the proposed multi-stream self-attention encoder blocks and rescoring the resultant lattices with neural network language models, we achieve the word error rate of 2.2% on the test-clean dataset of the LibriSpeech corpus, the best number reported thus far on the dataset.

Subfields: Artificial Intelligence, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Speech & Audio

Citations in the corpus

Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition (2020, background): “The papers corresponding to each data point have been collected in the bibliography [6, 8, 9, 13–21].”
Iterative Pseudo-Labeling for Speech Recognition (2020, positive): “Some of the most promising are from the Transformer family [1, 2, 3, 4, 5], which give state-of-the-art results on many ASR benchmarks and close the gap between end-to-end and hybrid systems.”
Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces (2020, unknown): “[48] 4g 2.”
Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions (2019, methodology): “Another very small ASR model was introduced by Han et al [13], which uses multiple parallel streams of self-attention with dilated, factorized, although not separable, 1D convo-lutions.”
The STC System for the CHiME-6 Challenge (2020, methodology): “We also observed a noticeable improvement after adding multi-stride [17] and multi-stream [18] self-attention layers into the model.”