Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview

Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski

Research output: Contribution to journalArticlepeer-review

Abstract

We present a structured overview of adaptation algorithms for neural network-based speech recognition, considering both hybrid hidden Markov model / neural network systems and end-to-end neural network systems, with a focus on speaker adaptation, domain adaptation, and accent adaptation. The overview characterizes adaptation algorithms as based on embeddings, model parameter adaptation, or data augmentation. We present a meta-analysis of the performance of speech recognition adaptation algorithms, based on relative error rate reductions as reported in the literature.
Original languageEnglish
Pages (from-to)33-66
Number of pages34
JournalIEEE Open Journal of Signal Processing
Volume2
Early online date16 Dec 2020
DOIs
Publication statusPublished - 2021

Keywords

  • accent adaptation
  • data augmentation
  • domain adaptation
  • regularization
  • semi-supervised learning
  • speaker adaptation
  • speaker embeddings
  • speech recognition
  • structured linear transforms

Fingerprint Dive into the research topics of 'Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview'. Together they form a unique fingerprint.

Cite this