Loading...
Please wait, while we are loading the content...
Similar Documents
Automatic Building of Synthetic Voices from Large Multi-Paragraph Speech Databases
| Content Provider | CiteSeerX |
|---|---|
| Author | Prahallad, Kishore Toth, Arthur R. |
| Abstract | Large multi paragraph speech databases encapsulate prosodic and contextual information beyond the sentence level which could be exploited to build natural sounding voices. This paper discusses our efforts on automatic building of synthetic voices from large multi-paragraph speech databases. We show that the primary issue of segmentation of large speech file could be addressed with modifications to forced-alignment technique and that the proposed technique is independent of the duration of the audio file. We also discuss how this framework could be extended to build a large number of voices from public domain large multi-paragraph recordings. Index Terms: speech synthesis, large multi-paragraph speech databases, forced-alignment, public domain recordings |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Large Multi-paragraph Speech Database Automatic Building Synthetic Voice Index Term Large Speech File Public Domain Large Multi-paragraph Recording Sentence Level Encapsulate Prosodic Large Multi Paragraph Speech Speech Synthesis Audio File Public Domain Recording Contextual Information Natural Sounding Voice Primary Issue Forced-alignment Technique |
| Content Type | Text |
| Resource Type | Article |
