Speaker clustering method for distributed microphone

Abstract

The invention relates to a speaker clustering method for a distributed microphone, which comprises the following steps: firstly performing pretreatment on signals acquired by the distributed microphone, further adopting the time delay estimation method for calculation against sound source signal fragments, getting a corresponding time delay estimation vector, then ruling out wrong data, performing speaker segmentation, and finally performing speaker clustering according to the speaker segmentation result. The distributed microphone is used as a signal acquisition and output device for calculating the time delay vector of the voice signal fragments, the time delay estimation precision is improved by ruling out the wrong data, and clustering algorithm is adopted for the time delay vector so as to respectively classify the voice signal fragments according to identities of speakers; furthermore, the device has the advantages of low price and convenience in use, and the speaker clustering method can be applied in a multi-person multi-party dialogue scene under a complex acoustic environment.

Description

technical field [0001] The invention belongs to the technical field of speech, and in particular relates to a speaker clustering method of distributed microphones. Background technique [0002] With the continuous development of network and communication technology, the use of existing multimedia technology, network and communication technology, distributed processing technology, etc. can realize multi-person and multi-party dialogue in complex acoustic environment scenarios. Traditional sound source input and recording equipment include head-mounted microphones, omnidirectional and directional single microphones, microphone arrays, etc. As a traditional sound source input and recording device, a single microphone has the advantages of small size and low price, but it does not have the ability to process environmental noise and locate the sound source; the microphone array is composed of multiple microphones arranged according to specific geometric positions. Spatial signal...

AI Technical Summary

Problems solved by technology

However, the calculation of the microphone array system is sensitive to the sampling error between each device, so the synchronization requirements for audio data are very strict; in the ordinary multi-person multi-party conference scene, the number of sound sources is unknown, the position of the microphone is unknown, and the acoustic environment of the room is unknown. That is, sound data needs to be processed in scenarios where both temporal and spatial prior information are missing.

[0007] As a single microphone for traditional sound source input and recording equipment, it is cheap and simple in structure. The disadvantage is that it is susceptible to environmental interference and cannot locate the sound source; the traditional microphone array system has been extensively studied, and the main reason for not commercializing The hardware is expensive and the algorithm complexity is high

Images