CLLGASOct 23, 2019

Speaker Adaptive Training using Model Agnostic Meta-Learning

arXiv:1910.10605v134 citations
Originality Incremental advance
AI Analysis

This addresses speaker adaptation in speech recognition, but it is incremental as it builds on existing meta-learning methods.

The paper tackled the problem of scaling speaker adaptive training for neural network acoustic models by formulating it as a meta-learning task, achieving results comparable to baseline and SAT-LHUC models.

Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of speaker dependent parameters that are jointly optimised with speaker independent parameters in order to remove speaker variation. However, this does not scale well if all neural network weights are to be adapted to the speaker. In this paper we formulate speaker adaptive training as a meta-learning task, in which an adaptation process using gradient descent is encoded directly into the training of the model. We compare our approach with test-only adaptation of a standard baseline model and a SAT-LHUC model with a learned speaker adaptation schedule and demonstrate that the meta-learning approach achieves comparable results.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes