How to get auto-labeled files in Chinese?

[Lyu T]

We can use festival to get auto-labeled files in English, is there any other tool to realize it in Chinese or other languages?

[Simon]

Festival alone cannot actually automatically label files. All it can do is process text through the front end to get a linguistic specification, which includes the sequence of phones.

The alignment is generally done using HMMs, often with the HTK toolkit.

For a language not supported by Festival, you need to use a TTS front-end, or be able to convert text into a string of phones some other way (e.g., by dictionary lookup). After that, the alignment step is the same as for English.

[YA]

In the “Front end” video in the Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit, Mr. Watts mentioned we need to search proper TTS front end for languages that are not supported by Festival. For example, Thai, Korean, Japanese, Cantonese and Mandarin.

Is there a recommended/efficient way/place/platform to conduct the search other than googling it?

Thanks!

[Simon]

There is no single index of all available TTS front-ends – the closest thing would be on the SynSIG website’s software list.

Availability varies widely with language, and for some there is no free software available.

So the short answer is “No – you’ll need to talk to your supervisor”.

[YA]

Hi Simon,

Hope you are well!
I am reading The Blizzard Challenge 2019 papers (http://www.festvox.org/blizzard/blizzard2019.html) and would like to know if there’s a way that we could listen to the synthetic voices submitted by different teams?

Also, please kindly advice if you prefer alumni to post questions in other venues (e.g. Linkedin or email).

Thank you!

[YA]

Emailed the Blizzard challenge support and found the synthetic speech of previous participants here: http://www.cstr.ed.ac.uk/projects/blizzard/data.html

[Author]

Posts