[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:00411] adaptation using HTS


Hello,
I am working on trying to provide a personalised synthesised English voice for a person with a progressive speech disorder. His speech is telegraphic, he has articulation difficulties and his speech is fairly unintelligible to a listener not used to hearing this type of speech. I have been able to get some recordings from him although obtaining a large amount of data is not possible. As the person's speech is distorted it may not be possible to make an intelligible voice for him following the usual steps as in the HTS-demo. For this reason it seems that an adaptation method, that I have read about in some of the HTS group's publications, would be more suitable. From previous postings I read that HTS does not yet support speaker adaptation using HEAdapt so is this still currently true? If anyone knows of any other adaptation work done with HTS, particularly whether any has been done in English, then I would really appreciate hearing about it.
Thanks very much,
Sarah Creer



Follow-Ups
[hts-users:00412] Re: adaptation using HTS, Heiga ZEN (Byung Ha CHUN)