Statistical Text-to-Speech Synthesis of Spanish Subtitles
| Autor: | Santiago Piqueras, Alfons Juan, Adrií Giménez, Jorge Civera, Miguel Angel Del-Agua |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Text-to-speech synthesis
business.industry Computer science Speech recognition Language barrier 020206 networking & telecommunications Speech synthesis 02 engineering and technology Accessibility computer.software_genre 030507 speech-language pathology & audiology 03 medical and health sciences Text to speech synthesis Video lectures 0202 electrical engineering electronic engineering information engineering Artificial intelligence Objective evaluation 0305 other medical science business Hidden Markov model LENGUAJES Y SISTEMAS INFORMATICOS computer Natural language processing Parametric statistics |
| Zdroj: | Advances in Speech and Language Technologies for Iberian Languages ISBN: 9783319136226 IberSPEECH RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia instname Scopus-Elsevier |
| Popis: | Online multimedia repositories are growing rapidly. However, language barriers are often difficult to overcome for many of the current and potential users. In this paper we describe a TTS Spanish sys- tem and we apply it to the synthesis of transcribed and translated video lectures. A statistical parametric speech synthesis system, in which the acoustic mapping is performed with either HMM-based or DNN-based acoustic models, has been developed. To the best of our knowledge, this is the first time that a DNN-based TTS system has been implemented for the synthesis of Spanish. A comparative objective evaluation between both models has been carried out. Our results show that DNN-based systems can reconstruct speech waveforms more accurately. The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no 287755 (transLectures) and ICT Policy Support Programme (ICT PSP/2007-2013) as part of the Competitiveness and Innovation Framework Programme (CIP) under grant agreement no 621030 (EMMA), and the Spanish MINECO Active2Trans (TIN2012-31723) research project. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|