Edinburgh Research Explorer

Segmental Recurrent Neural Networks for End-to-end Speech Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationProceedings of Interspeech 2016
Place of PublicationSan Francisco, United States
Pages385-389
Number of pages5
DOIs
Publication statusPublished - 12 Sep 2016
EventInterspeech 2016 - San Francisco, United States
Duration: 8 Sep 201612 Sep 2016
http://www.interspeech2016.org/

Conference

ConferenceInterspeech 2016
CountryUnited States
CitySan Francisco
Period8/09/1612/09/16
Internet address

Abstract

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous CRF-based acoustic models, it does not rely on an external system to provide features or segmentation boundaries. Instead, this model marginalises out all the possible segmentations, and features are extracted from the RNN trained together with the segmental CRF. In essence, this model is self-contained and can be trained end-to-end. In this paper, we discuss practical training and decoding issues as well as the method to speed up the training in the context of speech recognition. We performed experiments on the TIMIT dataset. We achieved 17.3 phone error rate (PER) from the first-pass decoding --- the best reported result using CRFs, despite the fact that we only used a zeroth-order CRF and without using any language model.

Event

Interspeech 2016

8/09/1612/09/16

San Francisco, United States

Event: Conference

Download statistics

No data available

ID: 26488857