Voice processing

A system comprising:

• an acoustic sensor and a voice processing device, the acoustic sensor being coupled to the voice processing device,
• wherein:
• the acoustic sensor is configured to capture a voice signal of a speaker;
• and
• the voice processing device is configured to:
• receive the voice signal of the speaker, and acquire a voiceprint feature of the speaker and position information of the speaker, the voiceprint feature including a lexical feature of a language spoken by the speaker;
• search for an identifier of the speaker in a speaker registry on the basis of the voiceprint feature of the speaker;
• update the speaker registry in response to determining that position information corresponding to the identifier of the speaker in the speaker registry is different from the position information of the speaker;
• and
• label the voice signal of the speaker with the identifier of the speaker, so as to track the speaker.

An apparatus comprising:

• one or more processors;
• and
• one or more memories storing thereon computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
• searching, on the basis of a voiceprint feature of a speaker, for an identifier of the speaker in a speaker registry, the voiceprint feature of the speaker including a parameter obtained according to a voice signal of the speaker captured by a microphone array and processed by a state machine including the following five states including a fuzzy state, a determined state, a critical state, a stable state, and a delay state;
• in response to determining that position information corresponding to the identifier of the speaker in the speaker registry is different from position information of the speaker, updating the speaker registry, the position information of the speaker including another parameter obtained according to the voice signal of the speaker captured by the microphone array;
• and
• labeling the voice signal of the speaker with the identifier of the speaker to track the speaker.