[hts-users:01725] Re: about utterance

[paminy <paminy@xxxxxxx>]

 

Thank you for you help ,Simon.

 

 

在2008-09-27，"Simon King" <Simon.King@xxxxxxxx> 写道：
>You have data with phoneme labels, but you want to get "full context" labels including prosodic contextual factors - correct?

>

yes

On the page of http://www.festvox.org/cmu_arctic/dbs_slt.html ,it said that "The database was automatically labelled using CMU Sphinx using the FestVox labelling scripts. No hand correction has been made."

Is there any descriptions about this process ?  How about the accuracy rate comaparing the manual labelling ?

>The normal way to obtain such labels is to predict them from the text, using a TTS front end. If you don't have a front end for your language, you could manually label the data - however, without a front end, you will not be able to automatically synthesise new sentences.
>

>If you are working on English, then Festival provides a front end that will predict the labels you need. For other languages, you will need to find a suitable front end from somewhere else.
>

Oh,you have tutored me how to get the labs from the text.Thanks again.

Dose it means that I coucd use the lab which is from the speech data 's text to creat the CART ? Or only for synthesis the text using the text's utt which is automatically generated from the festival ?

>If you are in this situation:
>
>- you have full context labels for some data (e.g., ARCTIC)
>- you have trained an average voice model on that data
>- you want to adapt that model to a target speaker using some new data
>- you only have phonetic labels for the new data
>
>then read this paper for a simple solution that appears to work quite well:
>
>Unsupervised Adaptation for HMM-Based Speech Synthesis. Simon King, Keiichi Tokuda, Heiga Zen, Junichi Yamagishi. Proc. Interspeech 2008, Brisbane, Australia. September 2008.
>
>I think I can send you a personal copy of this, if you don't have access to those proceedings.
>

 

I think the paper would be very helpful for me. I think I 'm in this situation of "you only have phonetic labels for the new data".

Sorry, I don't have the admission to get the paper "Unsupervised Adaptation for HMM-Based Speech Synthesis". I would be very appreciated if you send me a copy .

 

Thank you, once more .

 

Pang Minhui