Matches in SemOpenAlex for { <https://semopenalex.org/work/W2589926161> ?p ?o ?g. }
- W2589926161 endingPage "16" @default.
- W2589926161 startingPage "1" @default.
- W2589926161 abstract "Noise suppression and the estimation of the number of sources are two practical issues in applications of underdetermined blind source separation (UBSS). This paper proposes a noise-robust instantaneous UBSS algorithm for highly overlapped speech sources in the short-time Fourier transform (STFT) domain. The proposed algorithm firstly estimates the unknown complex-valued mixing matrix and the number of sources, which are then used to compute the STFT coefficients of corresponding sources at each auto-source time-frequency (TF) point. After that, the original sources are recovered by the inverse STFT. To mitigate the noise effect on the detection of auto-source TF points, we propose a method to effectively detect the auto-term location of the sources by using the principal component analysis (PCA) of the STFTs of noisy mixtures. The PCA-based detection method can achieve similar UBSS outcome as some filtering-based methods. More importantly, an efficient method to estimate the mixing matrix is proposed based on subspace projection and clustering approaches. The number of sources is obtained by counting the number of the resultant clusters. Evaluations have been carried out by using the speech corpus NOIZEUS and the experimental results have shown improved robustness and efficiency of the proposed algorithm." @default.
- W2589926161 created "2017-03-03" @default.
- W2589926161 creator A5003692319 @default.
- W2589926161 creator A5027778734 @default.
- W2589926161 creator A5034376590 @default.
- W2589926161 creator A5067222034 @default.
- W2589926161 creator A5068604294 @default.
- W2589926161 date "2017-05-01" @default.
- W2589926161 modified "2023-10-03" @default.
- W2589926161 title "Underdetermined blind separation of overlapped speech mixtures in time-frequency domain with estimated number of sources" @default.
- W2589926161 cites W1967834974 @default.
- W2589926161 cites W1970686290 @default.
- W2589926161 cites W1976806256 @default.
- W2589926161 cites W1981463705 @default.
- W2589926161 cites W1982172017 @default.
- W2589926161 cites W1985834699 @default.
- W2589926161 cites W1987619167 @default.
- W2589926161 cites W1987906574 @default.
- W2589926161 cites W1997231965 @default.
- W2589926161 cites W2013352441 @default.
- W2589926161 cites W2014452938 @default.
- W2589926161 cites W2021497665 @default.
- W2589926161 cites W2028693111 @default.
- W2589926161 cites W2029949825 @default.
- W2589926161 cites W2031583051 @default.
- W2589926161 cites W2038237443 @default.
- W2589926161 cites W2042860487 @default.
- W2589926161 cites W2043511730 @default.
- W2589926161 cites W2046233597 @default.
- W2589926161 cites W2050415164 @default.
- W2589926161 cites W2055034266 @default.
- W2589926161 cites W2057385319 @default.
- W2589926161 cites W2063385051 @default.
- W2589926161 cites W2067191022 @default.
- W2589926161 cites W2077626982 @default.
- W2589926161 cites W2079961989 @default.
- W2589926161 cites W2096327012 @default.
- W2589926161 cites W2096483602 @default.
- W2589926161 cites W2101616935 @default.
- W2589926161 cites W2105053623 @default.
- W2589926161 cites W2120847449 @default.
- W2589926161 cites W2122041143 @default.
- W2589926161 cites W2122885154 @default.
- W2589926161 cites W2126701296 @default.
- W2589926161 cites W2127851351 @default.
- W2589926161 cites W2130028685 @default.
- W2589926161 cites W2130780554 @default.
- W2589926161 cites W2133551681 @default.
- W2589926161 cites W2135158232 @default.
- W2589926161 cites W2135276891 @default.
- W2589926161 cites W2142638745 @default.
- W2589926161 cites W2144404214 @default.
- W2589926161 cites W2146182761 @default.
- W2589926161 cites W2150743271 @default.
- W2589926161 cites W2152374194 @default.
- W2589926161 cites W2153909896 @default.
- W2589926161 cites W2158456262 @default.
- W2589926161 cites W2164439948 @default.
- W2589926161 cites W2168273590 @default.
- W2589926161 cites W2168975387 @default.
- W2589926161 cites W2208938511 @default.
- W2589926161 cites W2281465390 @default.
- W2589926161 cites W2547878593 @default.
- W2589926161 cites W3163357387 @default.
- W2589926161 doi "https://doi.org/10.1016/j.specom.2017.02.003" @default.
- W2589926161 hasPublicationYear "2017" @default.
- W2589926161 type Work @default.
- W2589926161 sameAs 2589926161 @default.
- W2589926161 citedByCount "23" @default.
- W2589926161 countsByYear W25899261612017 @default.
- W2589926161 countsByYear W25899261612018 @default.
- W2589926161 countsByYear W25899261612019 @default.
- W2589926161 countsByYear W25899261612020 @default.
- W2589926161 countsByYear W25899261612021 @default.
- W2589926161 crossrefType "journal-article" @default.
- W2589926161 hasAuthorship W2589926161A5003692319 @default.
- W2589926161 hasAuthorship W2589926161A5027778734 @default.
- W2589926161 hasAuthorship W2589926161A5034376590 @default.
- W2589926161 hasAuthorship W2589926161A5067222034 @default.
- W2589926161 hasAuthorship W2589926161A5068604294 @default.
- W2589926161 hasConcept C102519508 @default.
- W2589926161 hasConcept C104317684 @default.
- W2589926161 hasConcept C11413529 @default.
- W2589926161 hasConcept C115961682 @default.
- W2589926161 hasConcept C120317606 @default.
- W2589926161 hasConcept C127162648 @default.
- W2589926161 hasConcept C134306372 @default.
- W2589926161 hasConcept C153180895 @default.
- W2589926161 hasConcept C154945302 @default.
- W2589926161 hasConcept C166386157 @default.
- W2589926161 hasConcept C179690561 @default.
- W2589926161 hasConcept C185592680 @default.
- W2589926161 hasConcept C203024314 @default.
- W2589926161 hasConcept C27438332 @default.
- W2589926161 hasConcept C28490314 @default.
- W2589926161 hasConcept C31258907 @default.
- W2589926161 hasConcept C32834561 @default.
- W2589926161 hasConcept C33923547 @default.