Empirical Evaluation Of Speaker Adaptation On DNN Based Acoustic Model

Abstract

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 spe

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keywang2018empirical

Related papers

• Bayesian Learning For Deep Neural Network Adaptation (2020)9.76
• Learning Hidden Unit Contributions For Unsupervised Acoustic Model Adaptation (2016)14.47
• Linear Networks Based Speaker Adaptation For Speech Synthesis (2018)6.34
• Learning To Adapt: A Meta-learning Approach For Speaker Adaptation (2018)9.76
• Unsupervised Model-based Speaker Adaptation Of End-to-end Lattice-free MMI Model For Speech Recognition (2022)2.26
• Exploring Gaussian Mixture Model Framework For Speaker Adaptation Of Deep Neural Network Acoustic Models (2020)0.00
• Speaker Adaptive Training Using Model Agnostic Meta-learning (2019)9.92
• Listen, Attend, Spell And Adapt: Speaker Adapted Sequence-to-sequence ASR (2019)8.82