Privacy-sensitive speech model creation via aggregation of multiple user models

摘要

Techniques disclosed herein include systems and methods for privacy-sensitive training data collection for updating acoustic models of speech recognition systems. In one embodiment, the system locally creates adaptation data from raw audio data. Such adaptation can include derived statistics and/or acoustic model update parameters. The derived statistics and/or updated acoustic model data can then be sent to a speech recognition server or third-party entity. Since the audio data and transcriptions are already processed, the statistics or acoustic model data is devoid of any information that could be human-readable or machine readable such as to enable reconstruction of audio data. Thus, such converted data sent to a server does not include personal or confidential information. Third-party servers can then continually update speech models without storing personal and confidential utterances of users.

主权项

1. A computer-implemented method of speech recognition processing, the computer-implemented method comprising:
receiving a spoken utterance; storing audio data from the spoken utterance at a first device; creating adaptation data for updating at least one acoustic model, the adaptation data being created from the audio data via processing at the first device, the adaptation data being in a format that hinders reconstruction of the audio data; and transmitting the adaptation data to a second device for processing.