Speaker Localization Based on Audio-Visual Bimodal Fusion

The demand for fluency in human–computer interaction is on an increase globally; thus, the active localization of the speaker by the machine has become a problem worth exploring. Considering that the stability and accuracy of the single-mode localization method are low, while the multi-mode localization method can utilize the redundancy of information to improve accuracy and anti-interference, a speaker localization method based on voice and image multimodal fusion is proposed. First, the voice localization method based on time differences of arrival (TDOA) in a microphone array and the face detection method based on the AdaBoost algorithm are presented herein. Second, a multimodal fusion method based on spatiotemporal fusion of speech and image is proposed, and it uses a coordinate system converter and frame rate tracker. The proposed method was tested by positioning the speaker stand at 15 different points, and each point was tested 50 times. The experimental results demonstrate that there is a high accuracy when the speaker stands in front of the positioning system within a certain range.

NMF-weighted SRP for multi-speaker direction of arrival estimation: robustness to spatial aliasing while exploiting sparsity in the atom-time domain

Localization of multiple speakers using microphone arrays remains a challenging problem, especially in the presence of noise and reverberation. State-of-the-art localization algorithms generally exploit the sparsity of speech in some representation for this purpose. Whereas the broadband approaches exploit time-domain sparsity for multi-speaker localization, narrowband approaches can additionally exploit sparsity and disjointness in the time-frequency representation. Broadband approaches are robust to spatial aliasing but do not optimally exploit the frequency domain sparsity, leading to poor localization performance for arrays with short inter-microphone distances. Narrowband approaches, on the other hand, are vulnerable to spatial aliasing, making them unsuitable for arrays with large inter-microphone spacing. Proposed here is an approach that decomposes a signal spectrum into a weighted sum of broadband spectral components (atoms) and then exploits signal sparsity in the time-atom representation for simultaneous multiple source localization. The decomposition into atoms is performed in situ using non-negative matrix factorization (NMF) of the short-term amplitude spectra and the localization estimate is obtained via a broadband steered-response power (SRP) approach for each active atom of a time frame. This SRP-NMF approach thereby combines the advantages of the narrowband and broadband approaches and performs well on the multi-speaker localization task for a broad range of inter-microphone spacings. On tests conducted on real-world data from public challenges such as SiSEC and LOCATA, and on data generated from recorded room impulse responses, the SRP-NMF approach outperforms the commonly used variants of narrowband and broadband localization approaches in terms of source detection capability and localization accuracy.