Background learning of speaker voices

A system for automatically identifying a speaker;

• the system includes:
• a speaker identifier operative to identify a speaker by:
• receiving a test utterance from the speaker;
• determining a most likely one of a plurality of speaker models for the test utterance;
• and
• identifying the speaker associated with the most likely speaker model as the speaker of the test utterance;
• and
• a speaker model generator operative to generate the plurality of speaker models, wherein the speaker model generator is operative to generate the plurality of speaker models in the background by:
• receiving training utterances from a pool of utterances from the plurality of speakers in the background, without prior knowledge of the speakers who spoke the respective training utterances;
• blind clustering of the training utterances from the pool of utterances based on a predetermined criterion, wherein the blind clustering includes calculating a likelihood vector for each training utterance;
• and
• non-explicitly training for each of the clusters a corresponding speaker model, each of the models representing a speaker.

A method for automatically identifying based on speech, comprising:

• receiving training utterances from a pool of utterances from the plurality of speakers;
• performing blind clustering of the received training utterances from the pool of utterances based on a predetermined criterion to produce clusters, wherein the blind clustering includes calculating a likelihood vector for each training utterance;
• non-explicitly training, for said clusters, corresponding speaker models representing associated speakers;
• receiving a test utterance from a speaker;
• determining a most likely one of said speaker models for the test utterance;
• and
• identifying a speaker associated with the determined most likely speaker model as the speaker of the test utterance,
• wherein said receiving training utterances occurs in the background, without prior knowledge of the speakers who respectively spoke said training utterances, and said speaker models are generated in the background.