Summary of the paper
| Title | Versatile Speech Databases for High Quality Synthesis for Basque |
|---|---|
| Authors | Iñaki Sainz, Daniel Erro, Eva Navas, Inma Hernáez, Jon Sánchez, Ibon Saratxaga and Igor Odriozola |
| Abstract | This paper presents three new speech databases for standard Basque. They are designed primarily for corpus-based synthesis but each database has its specific purpose: 1) AhoSyn: high quality speech synthesis (recorded also in Spanish), 2) AhoSpeakers: voice conversion and 3) AhoEmo3: emotional speech synthesis. The whole corpus design and the recording process are described with detail. Once the databases were collected all the data was automatically labelled and annotated. Then, an HMM-based TTS voice was built and subjectively evaluated. The results of the evaluation are pretty satisfactory: 3.70 MOS for Basque and 3.44 for Spanish. Therefore, the evaluation assesses the quality of this new speech resource and the validity of the automated processing presented. |
| Topics | Speech resource/database, Speech Synthesis, Corpus (creation, annotation, etc.) |
Full paper  |
Versatile Speech Databases for High Quality Synthesis for Basque |
| Bibtex | @InProceedings{SAINZ12.126, author = {Iñaki Sainz and Daniel Erro and Eva Navas and Inma Hernáez and Jon Sánchez and Ibon Saratxaga and Igor Odriozola}, title = {Versatile Speech Databases for High Quality Synthesis for Basque}, booktitle = {Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12)}, year = {2012}, month = {may}, date = {23-25}, address = {Istanbul, Turkey}, editor = {Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Thierry Declerck and Mehmet Uğur Doğan and Bente Maegaard and Joseph Mariani and Asuncion Moreno and Jan Odijk and Stelios Piperidis}, publisher = {European Language Resources Association (ELRA)}, isbn = {978-2-9517408-7-7}, language = {english} } |