Speaker separation based on real-time latent speaker state characterization

A system comprising:

• at least one processor;
• and
• a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
• obtaining a stream of audio waveform data that represents speech involving a plurality of speakers;
• as the stream of audio waveform data is obtained, determining a plurality of audio chunks, wherein an audio chunk is associated with one or more identity embeddings;
• segmenting the stream of audio waveform data into a plurality of segments based on the plurality of audio chunks and respective identity embeddings associated with the plurality of audio chunks, wherein a segment can be associated with a speaker included in the plurality of speakers;
• and
• providing information describing the plurality of segments associated with the stream of audio waveform data.

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform:

• obtaining a stream of audio waveform data that represents speech involving a plurality of speakers;
• as the stream of audio waveform data is obtained, determining a plurality of audio chunks, wherein an audio chunk is associated with one or more identity embeddings;
• segmenting the stream of audio waveform data into a plurality of segments based on the plurality of audio chunks and respective identity embeddings associated with the plurality of audio chunks, wherein a segment can be associated with a speaker included in the plurality of speakers;
• and
• providing information describing the plurality of segments associated with the stream of audio waveform data.