Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model
This work provides a needed experimental comparison for speaker adaptation methods in speech recognition, but it is incremental as it evaluates existing techniques on a specific accented dataset.
The paper conducted an empirical evaluation of three speaker adaptation methods (LIN, LHUC, KLD) on a TDNN-LSTM acoustic model to address speaker variability, particularly for accented Mandarin speakers, finding performance comparisons across different adaptation data sizes and accent degrees.
Speaker adaptation aims to estimate a speaker specific acoustic model from a speaker independent one to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. A variety of neural network adaptation methods have been proposed since deep learning models have become the main stream. But there still lacks an experimental comparison between different methods, especially when DNN-based acoustic models have been advanced greatly. In this paper, we aim to close this gap by providing an empirical evaluation of three typical speaker adaptation methods: LIN, LHUC and KLD. Adaptation experiments, with different size of adaptation data, are conducted on a strong TDNN-LSTM acoustic model. More challengingly, here, the source and target we are concerned with are standard Mandarin speaker model and accented Mandarin speaker model. We compare the performances of different methods and their combinations. Speaker adaptation performance is also examined by speaker's accent degree.