Assigning ssml tags to an audio corpus

Abstract

This disclosure describes a system that converts an audio object (e.g., an audio book, a podcast, a videoconference meeting) to text with SSML tags so that any future text-to-speech conversion enables speech synthesis to sound more human-like. The system analyzes the audio object to identify speech output characteristics for different tokens. Variations in speech output characteristics can distinguish between an utterance spoken by one character and an utterance spoken by another character. The system assigns the tokens to the characters and compares a speech output characteristic for a token to a baseline speech output characteristic associated with an identified character. Next, the system determines an amount of deviation between the speech output characteristic for the token and the baseline speech output characteristic. The system uses this deviation to determine a relative speech output characteristic value, which is to be included in an SSML tag for a token.