Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation

Abstract

This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) ---a method that linearly re-combines hidden units in a speaker- or environment-dependent manner using small amounts of unsupervised adaptation data. We also extend LHUC to a speaker adaptive training (SAT) framework that leads to a more adaptable DNN acoustic model, working both in a speaker-dependent and a speaker-independent manner, without the requirements to maintain auxiliary speaker-dependent feature extractors or to introduce significant speaker-dependent changes to the DNN structure. Through a series of experiments on four different speech recognition benchmarks (TED talks, Switchboard, AMI meetings, and Aurora4) comprising 270 test speakers, we show that LHUC in both its test-only and SAT variants results in consistent word error rate reductions ranging from 5% to 23% relative depending on the task and the degree of mismatch between training and test data. In addition, we have investigated the effect of the amount of adaptation data per speaker, the quality of unsupervised adaptation targets, the complementarity to other adaptation techniques, one-shot adaptation, and an extension to adapting DNNs trained in a sequence discriminative manner.

DOI: 10.1109/TASLP.2016.2560534

Extracted Key Phrases

0102020162017
Citations per Year

Citation Velocity: 10

Averaging 10 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.

Cite this paper

@article{Swietojanski2016LearningHU, title={Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation}, author={Pawel Swietojanski and Jinyu Li and Steve Renals}, journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, year={2016}, volume={24}, pages={1450-1463} }