On-the-fly Feature Based Speaker Adaptation for Dysarthric and Elderly Speech Recognition
Preprint
Abstract
Automatic recognition of dysarthric and elderly speech highly challenging tasks to date. Speaker-level heterogeneity attributed to accent or gender commonly found in normal speech, when aggregated with age and speech impairment severity, create large diversity among speakers. Speaker adaptation techniques play a crucial role in personalization of ASR systems for such users. Their mobility issues limit the amount of speaker-level data available for model based adaptation. To this end, this paper investigates two novel forms of feature based on-the-fly rapid speaker adaptation approaches. The first is based on speaker-level variance regularized spectral basis embedding (SBEVR) features, while the other uses on-the-fly learning hidden unit contributions (LHUC) transforms conditioned on speaker-level spectral features. Experiments conducted on the UASpeech dysarthric and DimentiaBank Pitt elderly speech datasets suggest the proposed SBEVR features based adaptation statistically significantly outperform both the baseline on-the-fly i-Vector adapted hybrid TDNN/DNN systems by up to 2.48% absolute (7.92% relative) reduction in word error rate (WER), and offline batch mode model based LHUC adaptation using all speaker-level data by 0.78% absolute (2.41% relative) in WER reduction.Keywords
All Related Versions
This publication has 49 references indexed in Scilit:
- Speaker adaptation of neural network acoustic models using i-vectors2013
- Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code2013
- Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription2011
- Adapting acoustic and lexical models to dysarthric speech2011
- Difficulties in Automatic Speech Recognition of Dysarthric Speakers and Implications for Speech-Based Applications Used by the Elderly: A Literature ReviewAssistive Technology, 2010
- Linear hidden transformations for adaptation of hybrid ANN/HMM modelsSpeech Communication, 2007
- Speaker normalization using efficient frequency warping procedures2002
- Speaker adaptation using constrained estimation of Gaussian mixturesIEEE Transactions on Speech and Audio Processing, 1995
- Subspace-based signal analysis using singular value decompositionProceedings of the IEEE, 1993
- Temporal Characteristics of the Speech of Normal Elderly AdultsJournal of Speech, Language, and Hearing Research, 1987