Edinburgh Research Explorer

SAT-LHUC: Speaker adaptive training for learning hidden unit contributions

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
Publication statusPublished - 1 Mar 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - China, Shanghai, China
Duration: 20 Mar 201625 Mar 2016


Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Abbreviated titleICASSP 2016
Internet address


This paper extends learning hidden unit contributions (LHUC) unsupervised speaker adaptation with speaker adaptive training (SAT). Contrary to other SAT approaches, the proposed technique does not require speaker-dependent features, the generation of auxiliary generative models to estimate or extract speaker-dependent information, or any changes to the speaker-independent model structure. SAT-LHUC is directly integrated into the objective and jointly learns speaker-independent and speaker-dependent representations. We demonstrate that the SAT-LHUC technique can match feature-space regression transforms for matched narrow-band data and outperform it on wide-band data when the runtime distribution differs significantly from training one. We have obtained 6.5%, 10% and 18.5% relative word error rate reductions compared to speaker-independent models on Switchboard, AMI meetings and TED lectures, respectively. This corresponds to relative gains of 2%, 4% and 6% compared with non-SAT LHUC adaptation. SAT-LHUC was also found to be complementary to SAT with feature-space maximum likelihood linear regression transforms.

Download statistics

No data available

ID: 23297584