A ground-breaking Expressive Text-To-Speech platform to create emotionally reson...
A ground-breaking Expressive Text-To-Speech platform to create emotionally resonant virtual voices
Traditional voice production process by voice actors in a studio environment is expensive, time consuming and difficult to adapt to multiple languages. Text to speech (TTS) solutions available in the market are trying to overcome...
ver más
¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video
Proyectos interesantes
TEC2012-38939-C03-01
INVESTIGACION AVANZADA EN TECNOLOGIAS DEL HABLA PARA APLICAC...
155K€
Cerrado
TIN2017-85854-C4-1-R
ANALISIS AFECTIVO DE INFORMACION MULTIMEDIA CON COMUNICACION...
100K€
Cerrado
BES-2016-077843
TECNOLOGIAS DE APRENDIZAJE PROFUNDO APLICADAS AL PROCESADO D...
93K€
Cerrado
PDC2022-133049-I00
SUBTITULADO AUTOMATICO MULTILINGUE PARA TRANSMISION EN DIREC...
123K€
Cerrado
YEWHA
Ye wha’? Class, Gender, Race and Age: Fixing Diversity in Te...
216K€
Cerrado
TEC2009-14094-C04-02
BUSQUEDA DE INFORMACION EN CONTENIDOS AUDIOVISUALES PLURILIN...
151K€
Cerrado
Información proyecto ETTS
Duración del proyecto: 24 meses
Fecha Inicio: 2022-06-17
Fecha Fin: 2024-06-30
Líder del proyecto
VOISEED SRL
No se ha especificado una descripción o un objeto social para esta compañía.
Presupuesto del proyecto
3M€
Fecha límite de participación
Sin fecha límite de participación.
Descripción del proyecto
Traditional voice production process by voice actors in a studio environment is expensive, time consuming and difficult to adapt to multiple languages. Text to speech (TTS) solutions available in the market are trying to overcome the bottlenecks in the traditional voice production pipeline, but fail to deliver the same level of emotion and prosody of human voices. To overcome these problems, Voiseed designed a ground-breaking Expressive TTS platform, driven by proprietary deep learning algorithms, to create virtual human-like voices, emotionally resonant, through a cost-efficient and time-saving process. Voiseed will offer Voice as a Service so that entertainment, e-learning and advertising companies will be enabled to generate and dub virtual voices into any target language, keeping the required prosody. During the project, Voiseed aims to develop a high quality unique expressive speech data set to release on the market a platform with more than 32 emotions in 16 languages.