Adaptive dictionary based approach for background noise and speaker classification and subsequent source separation

TL;DR

This paper presents an adaptive dictionary-based hierarchical approach for classifying background noise and speakers in noisy conversations, improving recognition and separation performance especially at low SNRs.

Contribution

It introduces a novel hierarchical method combining dictionary learning, block sparsity, and source recovery, with adaptive dictionary updates for unknown sources.

Findings

Speaker recognition rate improves by around 15% at 0 dB SNR.

Signal to distortion ratio improves by up to 10% at 0 dB SNR.

Adaptive dictionary learning performs well even when speakers or noises are outside trained sets.

Abstract

A judicious combination of dictionary learning methods, block sparsity and source recovery algorithm are used in a hierarchical manner to identify the noises and the speakers from a noisy conversation between two people. Conversations are simulated using speech from two speakers, each with a different background noise, with varied SNR values, down to -10 dB. Ten each of randomly chosen male and female speakers from the TIMIT database and all the noise sources from the NOISEX database are used for the simulations. For speaker identification, the relative value of weights recovered is used to select an appropriately small subset of the test data, assumed to contain speech. This novel choice of using varied amounts of test data results in an improvement in the speaker recognition rate of around 15% at SNR of 0 dB. Speech and noise are separated using dictionaries of the estimated speaker and noise, and an improvement of signal to distortion ratios of up to 10% is achieved at SNR of 0 dB. K-medoid and cosine similarity based dictionary learning methods lead to better recognition of the background noise and the speaker. Experiments are also conducted on cases, where either the background noise or the speaker is outside the set of trained dictionaries. In such cases, adaptive dictionary learning leads to performance comparable to the other case of complete dictionaries.