Regarding TTS (text to speech) SSML (https://www.w3.org/TR/speech-synthesis11/) seems now the standard language for speech Synthesis "metadata" specifications, to control aspects of speech such as pronunciation, volume, pitch, rate, etc. across different synthesis-capable platforms (It have been adopted as standard by Amazon Alexa, Google Actions, and others APIs).
Instead, regarding ASR (automatic speech recognition) Is there any similar standard for for sentiment analysis?
I mean, a possible standard of parameters recognizing sentiment analysis in a recorded speech? At the moment I didn't seen anything like that in famous Google Actions/Amazon Alexa platforms APIs. I'm wrong?
Any idea?