Latency-Controlled Neural Architecture Search for Streaming Speech Recognition

by   Liqiang He, et al.

Recently, neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). Our prior work has shown promising results compared with hand-designed neural networks. In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling. First, based on the vanilla neural architecture, normal cells are altered to be causal cells, in order to control the total latency of the neural network. Second, a revised operation space with a smaller receptive field is proposed to generate the final architecture with low latency. Extensive experiments show that: 1) Based on the proposed neural architecture, the neural networks with a medium latency of 550ms (millisecond) and a low latency of 190ms can be learned in the vanilla and revised operation space respectively. 2) For the low latency setting, the evaluation network can achieve more than 19% (average on the four test sets) relative improvements compared with the hybrid CLDNN baseline, on a 10k-hour large-scale dataset. Additional 11% relative improvements can be achieved if the latency of the neural network is relaxed to the medium latency setting.



There are no comments yet.


page 1

page 2

page 3

page 4


Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition

In this paper, we explore the neural architecture search (NAS) for autom...

SqueezeNAS: Fast neural architecture search for faster semantic segmentation

For real time applications utilizing Deep Neural Networks (DNNs), it is ...

Amortized Neural Networks for Low-Latency Speech Recognition

We introduce Amortized Neural Networks (AmNets), a compute cost- and lat...

Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications

In this paper, we summarize the application of transformer and its strea...

Neural Architecture Search for Speech Recognition

Deep neural networks (DNNs) based automatic speech recognition (ASR) sys...

FasterSeg: Searching for Faster Real-time Semantic Segmentation

We present FasterSeg, an automatically designed semantic segmentation ne...

A low latency ASR-free end to end spoken language understanding system

In recent years, developing a speech understanding system that classifie...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.