Segmental Intelligibility of Three Text-to-Speech Synthesis Methods in Reverberant Environments.
In this study, the segmental intelligibility of three currently available text-to-speech products under two reverberant conditions was investigated. The reverberation times used were 1.2 and 2.4 s simulating reverberation that may exist in a large room and a large hall with poor acoustics. The human...
| Publicado en: | AAC: Augmentative & Alternative Communication Vol. 20; no. 3; pp. 150 - 164 |
|---|---|
| Autor principal: | |
| Formato: | Artículo |
| Publicado: |
Taylor & Francis Ltd
Sep2004
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=14167146&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 14167146 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 07434618 9OD jtl: AAC: Augmentative & Alternative Communication issn: 07434618 maglogo: Y pubinfo: dt: Sep2004 vid: 20 iid: 3 pid: 377 pub: Taylor & Francis Ltd artinfo: ui: 14167146 10.1080/07434610410001699726 ppf: 150 ppct: 14 formats: tig: atl: Segmental Intelligibility of Three Text-to-Speech Synthesis Methods in Reverberant Environments. aug: au: Venkatagiri, Horabail S. affil: Iowa State University, Iowa, USA su: Intelligibility of speech Means of communication for people with disabilities Communication devices for people with disabilities Text processing (Computer science) Speech processing systems sug: subj: Intelligibility of speech Means of communication for people with disabilities Communication devices for people with disabilities Text processing (Computer science) Speech processing systems keyword: Augmentative and alternative communication Intelligibility Reverberation Text-to-speech synthesis ab: In this study, the segmental intelligibility of three currently available text-to-speech products under two reverberant conditions was investigated. The reverberation times used were 1.2 and 2.4 s simulating reverberation that may exist in a large room and a large hall with poor acoustics. The human speech had an overall intelligibility (whole words correct) of 95% and a phoneme error rate of 2.35% under reverberant conditions investigated in this study, which were not significantly different from those obtained in a nonreverberant controlled condition. In contrast, the overall intelligibility of text-to-speech voices was 68% and phoneme error rate was 14.48%, which indicated that that text-to-speech output suffers significantly in the same reverberant conditions. Implications of these findings for the improvement of text-to-speech products and the practice of AAC are discussed with suggestions for further research. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2004 holdings: @attributes: islocal: N |
|---|