Adaptation Algorithms for Speech Recognition: An Overview

Authors:
  • PBPeter Bell
    Peter Bell
  • JFJoachim Fainberg
    Joachim Fainberg
  • OKOndrej Klejch
    Ondrej Klejch
  • JLJinyu Li
    Jinyu Li
  • SRSteve Renals
    Steve Renals
  • PSPawel Swietojanski
    Pawel Swietojanski

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.