Uncertainty-based learning of acoustic models from noisy data
Saved in:
| Title: | Uncertainty-based learning of acoustic models from noisy data |
|---|---|
| Authors: | Ozerov, Alexey1 alexey.ozerov@technicolor.com, Lagrange, Mathieu2 mathieu.lagrange@ircam.fr, Vincent, Emmanuel3 emmanuel.vincent@inria.fr |
| Source: | Computer Speech & Language. May2013, Vol. 27 Issue 3, p874-894. 21p. |
| Subjects: | Acoustic models, Computational learning theory, Gaussian distribution, Decoding algorithms, Mathematical optimization, Gaussian mixture models, Hidden Markov models, Regression analysis |
| Abstract: | Abstract: We consider the problem of acoustic modeling of noisy speech data, where the uncertainty over the data is given by a Gaussian distribution. While this uncertainty has been exploited at the decoding stage via uncertainty decoding, its usage at the training stage remains limited to static model adaptation. We introduce a new expectation maximization (EM) based technique, which we call uncertainty training, that allows us to train Gaussian mixture models (GMMs) or hidden Markov models (HMMs) directly from noisy data with dynamic uncertainty. We evaluate the potential of this technique for a GMM-based speaker recognition task on speech data corrupted by real-world domestic background noise, using a state-of-the-art signal enhancement technique and various uncertainty estimation techniques as a front-end. Compared to conventional training, the proposed training algorithm results in 3–4% absolute improvement in speaker recognition accuracy by training from either matched, unmatched or multi-condition noisy data. This algorithm is also applicable with minor modifications to maximum a posteriori (MAP) or maximum likelihood linear regression (MLLR) acoustic model adaptation from noisy data and to other data than audio. [Copyright &y& Elsevier] |
| Copyright of Computer Speech & Language is the property of Academic Press Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
