NMF-weighted SRP for multi-speaker direction of arrival estimation: robustness to spatial aliasing while exploiting sparsity in the atom-time domain.
Sushmita ThakallapalliSuryakanth V. GangashettyNilesh MadhuPublished in: EURASIP J. Audio Speech Music. Process. (2021)
Keyphrases
- doa estimation
- direction of arrival
- signal subspace
- frequency domain
- negative matrix factorization
- canonical correlation analysis
- nonnegative matrix factorization
- high dimensional
- sparse representation
- linear array
- estimation error
- high frequency
- audio visual
- speech recognition
- sensor array
- parameter estimation
- hyperspectral
- reconstruction error
- antenna array
- denoising
- feature extraction