Automatic rate control based on user identities

摘要

Input media data with an input playing speed is received. One or more user identities are identified based at least in part on biometric data collected from one or more users who correspond to the one or more user identities and to whom audio utterance derived from the input media data is to be played. A preferred rate of audio utterance is determined based at least in part on the one or more user identities. A rate of audio utterance is determined for a portion of the input media data. Based at least in part on the preferred rate of audio utterance and the rate of audio utterance, a portion of audio output media data is generated with an output playing speed at which audio utterance in the portion of audio output media data is rendered with the preferred rate of audio utterance.

主权项

1. A method comprising:
receiving input media data with an input normal playback speed, the input media data comprising a plurality of input media data portions each having the same input normal playback speed; determining one or more user identities identified based at least in part on biometric data collected from one or more users who correspond to the one or more user identities and to whom audio utterance derived from the input media data is to be played; determining a preferred rate of audio utterance based at least in part on the one or more user identities; determining a plurality of rates of audio utterance for the plurality of input media data portions; based at least in part on the preferred rate of audio utterance and the plurality of rates of audio utterance, generating audio output media data comprising a plurality of output media data portions having at least two different output normal playback speeds but the same preferred rate of audio utterance; wherein the method is performed by one or more computing devices.