Neural net word representations for phrase-break prediction without a part of speech tagger

O. Watts, S. Gangireddy, J. Yamagishi, S. King, S. Renals, A. Stan, M. Giurgiu

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

Abstract

The use of shared projection neural nets of the sort used in language modelling is proposed as a way of sharing parameters between multiple text-to-speech system components. We experiment with pretraining the weights of such a shared projection on an auxiliary language modelling task and then apply the resulting word representations to the task of phrase-break prediction. Doing so allows us to build phrase-break predictors that rival conventional systems without any reliance on conventional knowledge-based resources such as part of speech taggers.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2599-2603
Number of pages5
ISBN (Print)9781479928927
DOIs
Publication statusPublished - 4 May 2014
EventICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Florence, Italy, Florence, United Kingdom
Duration: 4 May 20149 May 2014

Conference

ConferenceICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
CountryUnited Kingdom
CityFlorence
Period4/05/149/05/14

Keywords

  • multitask learning
  • neural net language modelling
  • Speech synthesis
  • TTS
  • unsupervised learning

Fingerprint Dive into the research topics of 'Neural net word representations for phrase-break prediction without a part of speech tagger'. Together they form a unique fingerprint.

Cite this