Edinburgh Research Explorer

Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise

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

Related Edinburgh Organisations

Open Access permissions

Open

Documents

  • Download as Adobe PDF

    Rights statement: alentini-Botinhao, C., Maia, R., Yamagishi, J., King, S., & Zen, H. (2012). Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise. In 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). (pp. 3997-4000). (IEEE International Conference on Acoustics Speech and Signal Processing). NEW YORK: IEEE. doi: 10.1109/ICASSP.2012.6288794

    Accepted author manuscript, 253 KB, PDF document

Original languageEnglish
Title of host publication2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Subtitle of host publicationKyoto, Japan
Place of PublicationNEW YORK
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages3997-4000
Number of pages4
ISBN (Electronic)978-1-4673-0044-5
ISBN (Print)978-1-4673-0045-2
DOIs
Publication statusPublished - 2012
EventIEEE International Conference on Acoustics, Speech and Signal Processing - Kyoto
Duration: 25 Mar 201230 Mar 2012

Publication series

NameIEEE International Conference on Acoustics Speech and Signal Processing
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)1520-6149

Conference

ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
CityKyoto
Period25/03/1230/03/12

Abstract

In this paper we introduce a new cepstral coefficient extraction method based on an intelligibility measure for speech in noise, the Glimpse Proportion measure. This new method aims to increase the intelligibility of speech in noise by modifying the clean speech, and has applications in scenarios such as public announcement and car navigation systems. We first explain how the Glimpse Proportion measure operates and further show how we approximated it to integrate it into an existing spectral envelope parameter extraction method commonly used in the HMM-based speech synthesis framework. We then demonstrate how this new method changes the modelled spectrum according to the characteristics of the noise and show results for a listening test with vocoded and HMM-based synthetic speech. The test indicates that the proposed method can significantly improve intelligibility of synthetic speech in speech shaped noise.

    Research areas

  • approximation theory, hidden Markov models, speech coding, speech synthesis, HMM-based speech synthesis framework, HMM-based synthetic speech intelligibility, car navigation systems, cepstral coefficient extraction method, clean speech modification, glimpse proportion measure, speech shaped noise, vocoded synthetic speech, Accuracy, Approximation methods, Cepstral analysis, Hidden Markov models, Noise, Noise measurement, Speech, HMM-based speech synthesis, Lombard speech, cepstral coefficient extraction, objective measure for speech intelligibility

Event

Download statistics

No data available

ID: 5855290