Improving Speech Recognition with Speech Synthesis-based Model Adapation

A system comprising:

• data processing hardware;
• and
• memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
• obtaining sample utterances of synthesized speech in a target domain;
• obtaining transcribed utterances of non-synthetic speech in the target domain;
• pre-training a speech recognition model on the sample utterances of synthesized speech in the target domain to attain an initial state for warm-start training;
• and
• after pre-training the speech recognition model, warm-start training the speech recognition model on the transcribed utterances of non-synthetic speech in the target domain to teach the speech recognition model to learn to recognize real/human speech in the target domain.