![]() Rick’s Spanish Speech:“Bienvenido a TechFest 2012, donde hoy se podrá ver de primera mano cómo Microsoft Research está estudiando las tendencias tecnológicas clave que definirán el siglo 21.” Click to Play Translating to Italian“Tu sai che io mai quando sono venuto a Microsoft non avrei mai immaginare che avremmo fatto questo e la ricerca qui.” Click to Play Translating to Spanish“Sabes que nunca, cuando llegué por primera vez a Microsoft nunca habría podido imaginar que íbamos a estar haciendo eso y la investigación aquí.” Click to Play Here is a sample of the recordings by his public speech.“You know I I never when I first came to Microsoft I would have never imagined that we would be doing that and research here. By using the new approach, we can synthesize any mixed language pair out of the 26 languages.ĭemo 2: Translating Rick Rashid’s English Speech to Many Languages We have recordings of 26 languages which are used to build our TTS of corresponding languages. Out of a speaker’s monolingual recordings, our algorithm can render speech sentences of different languages for building mixed-coded, bilingual TTS systems. ![]() We demo a new approach in turning monolingual TTS into multi-lingual TTS. However, it is usually difficult to find such a talent. The mixed-coded TTS can be easily built by a truly bilingual speaker. Sometimes it is even more desirable to have the response in mixed languages, For example, in a foreign country, it would be convenient if a user of car-navigation system who is not fluent in that particular foreign language could hear instructions in mixed-codes, such as entities like street names synthesized in the local language and routing directions in the user’s native language. Voice user interface needs to output responses in Text-To-Speech (TTS) synthesized speech. Sometimes it is even more desirable to have the response in mixed languages, For example, in a foreign country, it would be convenient if a user of car-navigation system who is not fluent in that particular foreign language could hear instructions in mixed-codes, such as entities like street names synthesized in the local language and routing directions in the user’s native language.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |