SPEECH RECOGNITION USING UNSPOKEN TEXT AND SPEECH SYNTHESIS

摘要

A method (500) for training a generative adversarial network (GAN)-based text-to-speech (TTS) model (310) and a speech recognition model (200) in unison includes obtaining a plurality of training text utterances (305) and generating, for output by the GAN-Based TTS model, a synthetic speech representation (306) of the corresponding training text utterance, and determining, using an adversarial discriminator (318), an adversarial loss term (320) indicative of an amount of acoustic noise disparity in a non- synthetic speech representation (304) relative to the corresponding synthetic speech representation of the corresponding training text utterance. The method also includes updating parameters of the GAN-based TTS model based on the adversarial loss term.