Context adaptive deep neural networks for fast acoustic model adaptation in noisy conditions

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 5270 - 5274
• Main Authors: Delcroix, Marc, Kinoshita, Keisuke, Chengzhu Yu, Ogawa, Atsunori, Yoshioka, Takuya, Nakatani, Tomohiro
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.03.2016
• Subjects: Acoustic model adaptation; Acoustic noise; Acoustics; Adaptation; Adaptation models; Automatic speech recognition; Computation; Conferences; Context; Context adaptive DNN; Context modeling; Deep neural networks; Factorized DNN; Mathematical models; Neural networks; Performance enhancement; Speech; Tasks; Training
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP.2016.7472683

Deep neural network (DNN) based acoustic models have greatly improved the performance of automatic speech recognition (ASR) for various tasks. Further performance improvements have been reported when making DNNs aware of the acoustic context (e.g. speaker or environment) for example by adding auxiliary features to the input, such as noise estimates or speaker i-vectors. We have recently proposed a context adaptive DNN (CA-DNN), which is another approach to exploit the acoustic context information within a DNN. A CA-DNN is a DNN that has one or several factorized layers, i.e. layers that use a different set of parameters to process each acoustic context class. The output of a factorized layer is obtained by the weighted sum over the contribution of the different context classes, given weights over the context classes. In our previous work, the class weights were computed independently of the recognizer. In this paper, we extend our previous work by introducing the joint training of the CA-DNN parameters and the class weights computation. Consequently, the class weights and the associated class definitions can be optimized for ASR. We report experimental results on the AURORA4 noisy speech recognition task showing the potential of our approach for fast unsupervised adaptation.