Work

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

Year: 2020

Type: article

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.

Source: IEEE Open Journal of Signal Processing

DOI: 10.1109/ojsp.2020.3045349

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

Institutions: University of Edinburgh, Microsoft (United States), UNSW Sydney, Apple (United Kingdom)

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,750