The Importance of Time-Frequency Averaging for Binaural Speaker Localization in Reverberant Environments

2020 ◽  
Author(s):  
Hanan Beit-On ◽  
Vladimir Tourbabin ◽  
Boaz Rafaely
Keyword(s):  
Time Frequency ◽  
Reverberant Environments ◽  
Speaker Localization

Robust Speaker Localization Guided by Deep Learning-Based Time-Frequency Masking

2019 ◽  
Vol 27 (1) ◽  
pp. 178-188 ◽  
Author(s):  
Zhong-Qiu Wang ◽  
Xueliang Zhang ◽  
DeLiang Wang
Keyword(s):  
Deep Learning ◽  
Time Frequency ◽  
Speaker Localization

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

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Sushmita Thakallapalli ◽  
Suryakanth V. Gangashetty ◽  
Nilesh Madhu
Keyword(s):  
Time Domain ◽  
Time Frame ◽  
Signal Spectrum ◽  
Real World Data ◽  
Localization Accuracy ◽  
Time Frequency ◽  
Spatial Aliasing ◽  
Localization Algorithms ◽  
Frequency Representation ◽  
Speaker Localization

AbstractLocalization 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.

Sign in / Sign up

Export Citation Format

Share Document