Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search

04/12/2021
by   Yukun Liu, et al.
0

Recently neural architecture search(NAS) has been successfully used in image classification, natural language processing, and automatic speech recognition(ASR) tasks for finding the state-of-the-art(SOTA) architectures than those human-designed architectures. NAS can derive a SOTA and data-specific architecture over validation data from a pre-defined search space with a search algorithm. Inspired by the success of NAS in ASR tasks, we propose a NAS-based ASR framework containing one search space and one differentiable search algorithm called Differentiable Architecture Search(DARTS). Our search space follows the convolution-augmented transformer(Conformer) backbone, which is a more expressive ASR architecture than those used in existing NAS-based ASR frameworks. To improve the performance of our method, a regulation method called Dynamic Search Schedule(DSS) is employed. On a widely used Mandarin benchmark AISHELL-1, our best-searched architecture outperforms the baseline Conform model significantly with about 11 efficient by the search cost comparisons.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/11/2020

Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients

Neural Architecture Search (NAS), the process of automating architecture...
04/07/2021

Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR

Neural architecture search (NAS) has been successfully applied to tasks ...
08/25/2020

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...
06/19/2019

Transfer NAS: Knowledge Transfer between Search Spaces with Transformer Agents

Recent advances in Neural Architecture Search (NAS) have produced state-...
07/07/2021

GLiT: Neural Architecture Search for Global and Local Image Transformer

We introduce the first Neural Architecture Search (NAS) method to find a...
03/14/2020

Efficient Backbone Search for Scene Text Recognition

Scene text recognition (STR) is very challenging due to the diversity of...
11/17/2019

Neural Recurrent Structure Search for Knowledge Graph Embedding

Knowledge graph (KG) embedding is a fundamental problem in mining relati...
This week in AI

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