Similarity-and-Independence-Aware Beamformer: Method for Target Source Extraction using Magnitude Spectrogram as Reference
This is an incremental improvement for audio source separation, specifically enhancing target signal accuracy in noisy environments.
The paper tackles target source extraction by proposing a similarity-and-independence-aware beamformer (SIBF) that uses a rough magnitude spectrogram as a reference, achieving more accurate extraction than DNN-based methods on the CHiME3 dataset.
This study presents a novel method for source extraction, referred to as the similarity-and-independence-aware beamformer (SIBF). The SIBF extracts the target signal using a rough magnitude spectrogram as the reference signal. The advantage of the SIBF is that it can obtain an accurate target signal, compared to the spectrogram generated by target-enhancing methods such as the speech enhancement based on deep neural networks (DNNs). For the extraction, we extend the framework of the deflationary independent component analysis, by considering the similarity between the reference and extracted target, as well as the mutual independence of all potential sources. To solve the extraction problem by maximum-likelihood estimation, we introduce two source model types that can reflect the similarity. The experimental results from the CHiME3 dataset show that the target signal extracted by the SIBF is more accurate than the reference signal generated by the DNN. Index Terms: semiblind source separation, similarity-and-independence-aware beamformer, deflationary independent component analysis, source model