Semi-Supervised Speaker Adaptation for In-Vehicle Speech Recognition with Deep Neural Networks


In this paper, we present a new i-vector based speaker adaptation method for automatic speech recognition with deep neural networks, focusing on in-vehicle scenarios. Our proposed method is, rather than augmenting i-vectors to acoustic feature vectors to form concatenated input vectors for adapting neural network acoustic model parameters, is to perform… (More)
DOI: 10.21437/Interspeech.2016-1625


3 Figures and Tables