3

I am developing a PoC using Watson text to speech and Watson conversation.

Sometimes, the chatbot needs to ask a question, so I'd like text to speech to synthesize the voice using an interrogation intonation.

Is it possible to be done?

Simon O'Doherty
  • 9,259
  • 3
  • 26
  • 54
Leo
  • 751
  • 4
  • 29

3 Answers3

3

Watson Text to Speech supports SSML, and has expressive SSML tags.

The one you want to use is Uncertainty. As it is defined as "conveys an uncertain, interrogative message".

Example: 

<express-as type="Uncertainty">
  Could she still be in the office? She told me that she might leave early.
</express-as>

More details on it's usage is here:

https://console.bluemix.net/docs/services/text-to-speech/SSML-expressive.html#the-express-as-element

Simon O'Doherty
  • 9,259
  • 3
  • 26
  • 54
  • 1
    Hi Simon. Not for all voices. I am using Isabela's voice (PT-BR), which is the only voice in Brazillian Portuguese available,which does not seem to support SSML tags. However, since my question is obviously incomplete (I haven't mentioned which voice I was using) and since your answer actually is the right answer, I will accept it and close this. – Leo Oct 30 '17 at 11:38
1

Yes, you can certainly use text-to-speech (TTS) for output and speech-to-text (STT) for input. You would need to use a middleware or app layer to drive the conversation and route the input/output to the other services (see "how to use" in the docs).

I have used the following TJBot recipe as a simple and good started for some projects: https://github.com/damiancummins/tell_the_time

data_henrik
  • 16,724
  • 2
  • 28
  • 49
  • Hi. I am sorry, maybe I was not clear. My question is regarding TTS support to generate audio with the correct intonation for questions. – Leo Oct 26 '17 at 13:23
  • With the TTS service you can generate the correct intonation (I have done that for some English words in German). But again, the TTS is another component that needs to be coordinated via an app or middleware layer. – data_henrik Oct 26 '17 at 13:27
  • I am using the Brazilian Portuguese voice and it seems to ignore the question mark in the end of the statement – Leo Oct 26 '17 at 13:40
  • I am trying with the TTS demo and it seems that for some voices, the question mark is correctly interpreted (such as Allison). I believe voices have different SSML support, and probably Isabela has no support for it – Leo Oct 26 '17 at 17:37
1

Unfortunately Concatenative TTS may have problems to create correct intonation in questions. If you think it happens consistently or too often please open a bug. If you have a specific question which gets incorrect intonation try to rephrase it a little bit if possible. A useful trick for this voice could be to use double question mark '??'

Radek Kazbunda
  • 11
  • 1