Realtime acoustic adaptation using stability measures

A computer-implemented method comprising:

• receiving a first portion of a speech session;
• decoding the first portion of the speech session to generate a transcription of the first portion of the speech session using a speaker adaptation profile;
• identifying a segment of the transcription of the first portion of the speech session;
• determining a stability measure of the segment;
• determining that the stability measure for the segment satisfies a threshold;
• in response to determining that the stability measure for the segment satisfies the threshold, triggering real-time update of the speaker adaptation profile using the segment, or using a portion of speech data that corresponds to the segment;
• receiving a second portion of the speech session;
• decoding the second portion of the speech session to generate a transcription of the second portion of the speech session using the updated speaker adaptation profile;
• and
• outputting a set of transcriptions comprising the transcription of the first portion of the speech session and the transcription of the second portion of the speech session.

A system comprising:

• one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• receiving a transcription of a first portion of a speech session, wherein the transcription of the first portion of the speech session is generated using a speaker adaptation profile;
• receiving a stability measure for a segment of the transcription;
• determining that the stability measure for the segment satisfies a threshold;
• in response to determining that the stability measure for the segment satisfies the threshold, triggering a real-time update of the speaker adaptation profile using the segment, or using a portion of speech data that corresponds to the segment;
• receiving a transcription of a second portion of the speech session, wherein the transcription of the second portion of the speech session is generated using the updated speaker adaptation profile;
• and
• outputting a set of transcriptions comprising the transcription of the first portion of the speech session and the transcription of the second portion of the speech session.

A computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

• receiving a first portion of a speech session;
• decoding the first portion of the speech session to generate a transcription of the first portion of the speech session using a speaker adaptation profile;
• identifying a segment of the transcription of the first portion of the speech session;
• determining a stability measure of the segment;
• determining that the stability measure for the segment satisfies a threshold;
• in response to determining that the stability measure for the segment satisfies the threshold, triggering real-time update of the speaker adaptation profile using the segment, or using a portion of speech data that corresponds to the segment;
• receiving a second portion of the speech session;
• decoding the second portion of the speech session to generate a transcription of the second portion of the speech session using the updated speaker adaptation profile;
• and
• outputting a set of transcriptions comprising the transcription of the first portion of the speech session and the transcription of the second portion of the speech session.