CUED Publications database

Structured discriminative models using deep neural-network features

Van Dalen, RC and Yang, J and Wang, H and Ragni, A and Zhang, C and Gales, MJF (2016) Structured discriminative models using deep neural-network features. In: UNSPECIFIED pp. 160-166..

Full text not available from this repository.


© 2015 IEEE. State-of-the-art speech recognisers employ neural networks in various configurations. A standard (hybrid) speech recogniser computes the likelihood for one time frame and state, using only one out of thousands of possible neural-network outputs. However, the whole output vector carries information. In this paper, features from state-of-the-art speech recognisers are collected per phone given a particular context, and input to a discriminative log-linear model. The log-linear model is trained with conditional maximum likelihood or a large-margin criterion. A key element is the prior on the parameters of the log-linear model. The mean of the prior is set to the point where the performance of the original systems is attained. The log-linear model then provides an additional increase over the state-of-the-art performance of the individual systems.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:41
Last Modified: 22 May 2018 07:18