I work on expressive speech synthesis and I don't know if the simple fact of synthesizing expressive speech in a different language is in and of itself an originality. Suppose I only use existing methods and only synthesize speech in a different language, but without bringing anything new on a technical level. What is your opinion?
Dear Lyes, It is very difficult to answer yes to your question. The conditio sine qua non for any research is to elaborate a careful state-of-the-art, and this entails knowing all previous and contemporary developments in nearly any major language; say, English, French, German, Italian, Spanish, f.i.
A well elaborated state-of-the-art will provide you solid grounds for the originality of your work. Regaldless of the language you' re writing your own research.
I agree with Sascha. There is the phenomenon of phoneme substitution in non native speakers. One area that I would also look at is phonological feature behavior in foreign speakers..
How these elements play into syllable composition for "accented" voice generation would be interesting to explore.
There are definitely a lot of interesting research questions and implementation challenges in this area. Languages employ different strategies to express emotion, prosody and intonation to the extend that transposing a global contour would miss a lot of details. Sometimes one is lucky. Sometimes the results can be quite problematic.
Consider one example: One of strategies to ask question in English is to have a rising intonation on the last syllable. The degree of rising can be linked to some emotional characteristics. Transposing this strategy to Chinese may result in a change of lexical tone, therefore changing a word in the sentence.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Human-Computer Interaction