Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Para optimizar los resultados de la búsqueda, se recomienda utilizar términos en inglés.

Sistema de reconocimiento del habla y traducción multilingüe para dispositivos de computación móviles

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOSG20190108006
Publicado:
04/02/2019
Caducidad:
05/02/2020
Resumen:
Un instituto de investigación singapurense ha construido un software de traducción y transcripción de voz a texto (S2T) multilingüe y de bajo coste para smartphones, dispositivos móviles, tabletas y ordenadores portátiles que permite una comunicación eficaz de personas con discapacidad. Este sistema es capaz de reconocer 81 idiomas, como inglés, chino, tamil y malayo. La gestión y soporte de bibliotecas multilingües se gestiona desde un servidor, que envía actualizaciones constantes del software al dispositivo final. El sistema permite la comunicación en tiempo real de personas sordas y ancianos. Otras áreas de aplicación potenciales incluyen cuidado de pacientes en hospitales y atención al cliente en tiendas. El instituto busca pymes de cualquier tamaño y multinacionales con el fin de licenciar la tecnología y establecer acuerdos de cooperación en materia de investigación.

Details

Tittle:
Multilingual speech recognition and translation system for mobile computing devices
Summary:
A Singapore academic and research institute has built a low-cost multilingual speech-to-text (S2T) transcription and translation software that runs on smartphones, mobile devices, tablets, and laptops, enabling effective communication for people with disabilities. The institute seeks partnerships with SMEs of any sizes and MNEs through technology licensing or research cooperation agreements.
Description:
The institute has developed a speech-to-text transcriber/translator that can recognize 81 languages, including English, Chinese, Tamil, and Malay, among others.

Enterprises and original equipment manufacturers are increasingly making efforts to embed speech and voice recognition technology into their devices. The software allows the transcription of speech and voice to be conducted both in silent and noisy environments. The speech-to-text transcriber/translator uses a natural language processing engine that recognizes the voice of a person and converts it into text to match the words present in the database.

The management and support of multi-language libraries are handled by a server, which sends constant updates of software to the end-device, such as extension of words to the language libraries.

The speech-to-text transcriber/translator provides effective real-time communication for the deaf and elderly. Other potential application areas for the software include patient care in hospitals and customer care in retail outlets. It can be used as a note-taking tool for students and secretaries and as a language translator for travellers. Moreover, it provides captions for radios, live television broadcasts, movies and digital media files and acts as a virtual assistant and voice automation tool.

The institute is keen to establish partnerships with SMEs of any sizes or MNCs. The desired type of partnership would be in the form of a licensing or research cooperation agreement.
Advantages and Innovations:
Some of the advantages of the speech-to-text transcriber/translator are the following:

· It is a low-cost tool
· It can convert speech from different kinds of accents spoken across multi-cultural societies.
· It can convert speech without any stoppage in between, and supports many-to-one communications in open spaces or indoor environments.
Stage of Development:
Prototype available for demonstration
IPs:
Copyright

Partner sought

Type and Role of Partner Sought:
The Singapore institute seeks to partner SMEs of all sizes and MNEs through the following types of partnerships:

i) A license agreement where the partner can license the technology and develop further to incorporate/integrate into its software or solutions.

ii) A research cooperation agreement where both parties could collaborate to co-develop further to cater to the needs of specific customer/market segments.

Client

Type and Size of Client:
R&D Institution
Already Engaged in Trans-National Cooperation:
Si
Languages Spoken:
English

Keywords

Technology Keywords:
01003017 Speech Processing/Technology