Automatic Building of Synthetic Voices from Audio Books
Current state-of-the-art text-to-speech systems produce intelligible utterances, but lack the prosody of natural speech. This is due to poor models of prosody built from single sentence recordings such as CMU ARCTIC. Building better models of prosody involves development of prosodically rich speech...
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Text |
Language: | English |
Published: |
2010
|
Subjects: | |
Online Access: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.9765 http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf |
id |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.207.9765 |
---|---|
record_format |
openpolar |
spelling |
ftciteseerx:oai:CiteSeerX.psu:10.1.1.207.9765 2023-05-15T15:02:26+02:00 Automatic Building of Synthetic Voices from Audio Books Kishore Prahallad Mosur Ravishankar Tanja Schultz The Pennsylvania State University CiteSeerX Archives 2010 application/pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.9765 http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf en eng http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.9765 http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf Metadata may be used without restrictions as long as the oai identifier remains attached to it. http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf Speech synthesis audio books voice conversion speaker-specific text 2010 ftciteseerx 2016-01-07T17:42:48Z Current state-of-the-art text-to-speech systems produce intelligible utterances, but lack the prosody of natural speech. This is due to poor models of prosody built from single sentence recordings such as CMU ARCTIC. Building better models of prosody involves development of prosodically rich speech databases. However, development of such speech databases requires a large amount of effort and time. An alternative is to exploit story style monologues (long speech files) in audio books. These monologues already encapsulate rich prosody including varied intonation contours, pitch accents and phrasing patterns. Thus, audio books act as excellent candidates for building prosodic models and natural sounding synthetic voices. The processing of such audio books poses several challenges including segmentation of long speech files, detection of mispronunciations, extraction and evaluation of representations of prosody. Text Arctic Unknown Arctic |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
ftciteseerx |
language |
English |
topic |
Speech synthesis audio books voice conversion speaker-specific |
spellingShingle |
Speech synthesis audio books voice conversion speaker-specific Kishore Prahallad Mosur Ravishankar Tanja Schultz Automatic Building of Synthetic Voices from Audio Books |
topic_facet |
Speech synthesis audio books voice conversion speaker-specific |
description |
Current state-of-the-art text-to-speech systems produce intelligible utterances, but lack the prosody of natural speech. This is due to poor models of prosody built from single sentence recordings such as CMU ARCTIC. Building better models of prosody involves development of prosodically rich speech databases. However, development of such speech databases requires a large amount of effort and time. An alternative is to exploit story style monologues (long speech files) in audio books. These monologues already encapsulate rich prosody including varied intonation contours, pitch accents and phrasing patterns. Thus, audio books act as excellent candidates for building prosodic models and natural sounding synthetic voices. The processing of such audio books poses several challenges including segmentation of long speech files, detection of mispronunciations, extraction and evaluation of representations of prosody. |
author2 |
The Pennsylvania State University CiteSeerX Archives |
format |
Text |
author |
Kishore Prahallad Mosur Ravishankar Tanja Schultz |
author_facet |
Kishore Prahallad Mosur Ravishankar Tanja Schultz |
author_sort |
Kishore Prahallad |
title |
Automatic Building of Synthetic Voices from Audio Books |
title_short |
Automatic Building of Synthetic Voices from Audio Books |
title_full |
Automatic Building of Synthetic Voices from Audio Books |
title_fullStr |
Automatic Building of Synthetic Voices from Audio Books |
title_full_unstemmed |
Automatic Building of Synthetic Voices from Audio Books |
title_sort |
automatic building of synthetic voices from audio books |
publishDate |
2010 |
url |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.9765 http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf |
op_relation |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.9765 http://www.lti.cs.cmu.edu/Research/Thesis/sunkeswari,%20kishore.pdf |
op_rights |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
_version_ |
1766334387847168000 |