Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
Open Access
- 16 December 2020
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Signal Processing
- Vol. 2, 33-66
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.Keywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council (EP/R012180/1)
- Bloomberg
- EU H2020 (825627)
- Office of the Director of National Intelligence
- Intelligence Advanced Research Projects Activity
- Air Force Research Laboratory (#FA8650-17-C-9117)
This publication has 228 references indexed in Scilit:
- Unleashing the killer corpus: experiences in creating the multi-everything AMI Meeting CorpusLanguage Resources and Evaluation, 2007
- Rapid speaker adaptation in eigenvoice spaceIEEE Transactions on Speech and Audio Processing, 2000
- Cluster adaptive training of hidden Markov modelsIEEE Transactions on Speech and Audio Processing, 2000
- Continuous probabilistic transform for voice conversionIEEE Transactions on Speech and Audio Processing, 1998
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Neural networks for statistical recognition of continuous speechProceedings of the IEEE, 1995
- Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chainsIEEE Transactions on Speech and Audio Processing, 1994
- A cache-based natural language model for speech recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Adaptation of automatic speech recognizers to new speakers using canonical correlation analysis techniquesComputer Speech & Language, 1986