CUED Publications database

Stimulated training for automatic speech recognition and keyword search in limited resource conditions

Ragni, A and Wu, C and Gales, MJF and Vasilakes, J and Knill, KM (2017) Stimulated training for automatic speech recognition and keyword search in limited resource conditions. In: UNSPECIFIED pp. 4830-4834..

Full text not available from this repository.

Abstract

© 2017 IEEE. Training neural network acoustic models on limited quantities of data is a challenging task. A number of techniques have been proposed to improve generalisation. This paper investigates one such technique called stimulated training. It enables standard criteria such as cross-entropy to enforce spatial constraints on activations originating from different units. Having different regions being active depending on the input unit may help network to discriminate better and as a consequence yield lower error rates. This paper investigates stimulated training for automatic speech recognition of a number of languages representing different families, alphabets, phone sets and vocabulary sizes. In particular, it looks at ensembles of stimulated networks to ensure that improved generalisation will withstand system combination effects. In order to assess stimulated training beyond 1-best transcription accuracy, this paper looks at keyword search as a proxy for assessing quality of lattices. Experiments are conducted on IARPA Babel program languages including the surprise language of OpenKWS 2016 competition.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 03 Aug 2017 02:37
Last Modified: 26 Oct 2017 01:55
DOI: