Edinburgh Research Explorer

Evaluating speech intelligibility enhancement for 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: © King, S., Yamagishi, J., & Valentini-Botinhao, C. (2012). Evaluating speech intelligibility enhancement for HMM-based synthetic speech in noise. In Proc. SAPA-SCALE Workshop on Statistical and Perceptual Audition (SAPA-SCALE 2012). Portland, OR, USA .

    Accepted author manuscript, 635 KB, PDF-document

Original languageEnglish
Title of host publicationProc. SAPA-SCALE Workshop on Statistical and Perceptual Audition (SAPA-SCALE 2012)
Place of PublicationPortland, OR, USA
Publication statusPublished - 2012

Abstract

It is possible to increase the intelligibility of speech in noise by enhancing the clean speech signal. In this pa- per we demonstrate the effects of modifying the spectral envelope of synthetic speech according to the environ- mental noise. To achieve this, we modify Mel cepstral coefficients according to an intelligibility measure that accounts for glimpses of speech in noise: the Glimpse Proportion measure. We evaluate this method against a baseline synthetic voice trained only with normal speech and a topline voice trained with Lombard speech, as well as natural speech. The intelligibility of these voices was measured when mixed with speech-shaped noise and with a competing speaker at three different levels. The Lom- bard voices, both natural and synthetic, were more intelli- gible than the normal voices in all conditions. For speech- shaped noise, the proposed modified voice was as intel- ligible as the Lombard synthetic voice without requiring any recordings of Lombard speech, which are hard to ob- tain. However, in the case of competing talker noise, the Lombard synthetic voice was more intelligible than the proposed modified voice.

Download statistics

No data available

ID: 3543364