Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
Audio and Speech Processing
2021-03-02 v2 Computation and Language
Sound
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.
Cite
@article{arxiv.2008.06580,
title = {Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview},
author = {Peter Bell and Joachim Fainberg and Ondrej Klejch and Jinyu Li and Steve Renals and Pawel Swietojanski},
journal= {arXiv preprint arXiv:2008.06580},
year = {2021}
}
Comments
Total of 31 pages, 27 figures. Associated repository: https://github.com/pswietojanski/ojsp_adaptation_review_2020