Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition

Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Kevin Duh

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The state-of-the-art large vocabulary speech recognition systems consist of several components including hidden Markov model (HMM) and deep neural network (DNN). To realize the highest recognition performance, numerous metaparameters specifying the designs and training setups of these components must be optimized. A prominent obstacle in system development is the laborious effort required by human experts in tuning these meta-parameters. To automate the process, we propose to tune the meta-parameters of a whole large vocabulary speech recognition system using the evolution strategy with a multi-objective Pareto optimization. As the result of the evolution, the system is optimized for both low word error rate (WER) and compact model size. Since the approach requires repeated training and evaluation of the recognition systems that require large computation, we make use of parallel computation on cloud computers. Experimental results show the effectiveness of the proposed approach by discovering appropriate configuration for large vocabulary speech recognition systems automatically.

Original languageEnglish
JournalIEEE/ACM Transactions on Audio Speech and Language Processing
DOIs
Publication statusAccepted/In press - 2018 Jan 1
Externally publishedYes

Keywords

  • CMA-ES
  • Deep neural network
  • Genetic algorithm
  • Genetic algorithms
  • Hidden Markov models
  • Multi-objective optimization
  • Optimization
  • Speech processing
  • Speech recognition
  • Speech recognition
  • Training
  • Vocabulary

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Acoustics and Ultrasonics
  • Computational Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition'. Together they form a unique fingerprint.

Cite this