Speaker adaptation and adaptive training for jointly optimised tandem systems
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
MetadataShow full item record
Wang, Y., Zhang, C., Gales, M., & Woodland, P. (2018). Speaker adaptation and adaptive training for jointly optimised tandem systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2018-September 872-876. https://doi.org/10.21437/Interspeech.2018-2432
Speaker independent (SI) Tandem systems trained by joint optimisation of bottleneck (BN) deep neural networks (DNNs) and Gaussian mixture models (GMMs) have been found to produce similar word error rates (WERs) to Hybrid DNN systems. A key advantage of using GMMs is that existing speaker adaptation methods, such as maximum likelihood linear regression (MLLR), can be used which to account for diverse speaker variations and improve system robustness. This paper investigates speaker adaptation and adaptive training (SAT) schemes for jointly optimised Tandem systems. Adaptation techniques investigated include constrained MLLR (CMLLR) transforms based on BN features for SAT as well as MLLR and parameterised sigmoid functions for unsupervised test-time adaptation. Experiments using English multi-genre broadcast (MGB3) data show that CMLLR SAT yields a 4% relative WER reduction over jointly trained Tandem and Hybrid SI systems, and further reductions in WER are obtained by system combination.
External DOI: https://doi.org/10.21437/Interspeech.2018-2432
This record's URL: https://www.repository.cam.ac.uk/handle/1810/286180