Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380714525> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4380714525 abstract "In this paper, we present a statistical beamforming algorithm as a pre-processing step for robust automatic speech recognition (ASR). By modeling the target speech as a non-stationary Laplacian distribution, a mask-based statistical beamforming algorithm is proposed to exploit both its output and masked input variance for robust estimation of the beamformer. In addition, we also present a method for steering vector estimation (SVE) based on a noise power ratio obtained from the target and noise outputs in independent component analysis (ICA). To update the beamformer in the same ICA framework, we derive ICA with distortionless and null constraints on target speech, which yields beamformed speech at the target output and noises at the other outputs, respectively. The demixing weights for the target output result in a statistical beamformer with the weighted spatial covariance matrix (wSCM) using a weighting function characterized by a source model. To enhance the SVE, the strict null constraints imposed by the Lagrange multiplier methods are relaxed by generalized penalties with weight parameters, while the strict distortionless constraints are maintained. Furthermore, we derive an online algorithm based on an optimization technique of recursive least squares (RLS) for practical applications. Experimental results on various environments using CHiME-4 and LibriCSS datasets demonstrate the effectiveness of the presented algorithm compared to conventional beamforming and blind source extraction (BSE) based on ICA on both batch and online processing." @default.
- W4380714525 created "2023-06-15" @default.
- W4380714525 creator A5031280750 @default.
- W4380714525 creator A5045121959 @default.
- W4380714525 date "2023-06-13" @default.
- W4380714525 modified "2023-10-16" @default.
- W4380714525 title "Statistical Beamformer Exploiting Non-stationarity and Sparsity with Spatially Constrained ICA for Robust Speech Recognition" @default.
- W4380714525 doi "https://doi.org/10.48550/arxiv.2306.07562" @default.
- W4380714525 hasPublicationYear "2023" @default.
- W4380714525 type Work @default.
- W4380714525 citedByCount "0" @default.
- W4380714525 crossrefType "posted-content" @default.
- W4380714525 hasAuthorship W4380714525A5031280750 @default.
- W4380714525 hasAuthorship W4380714525A5045121959 @default.
- W4380714525 hasBestOaLocation W43807145251 @default.
- W4380714525 hasConcept C11413529 @default.
- W4380714525 hasConcept C115961682 @default.
- W4380714525 hasConcept C126838900 @default.
- W4380714525 hasConcept C153180895 @default.
- W4380714525 hasConcept C154945302 @default.
- W4380714525 hasConcept C163294075 @default.
- W4380714525 hasConcept C183115368 @default.
- W4380714525 hasConcept C185142706 @default.
- W4380714525 hasConcept C2776182073 @default.
- W4380714525 hasConcept C28490314 @default.
- W4380714525 hasConcept C33378366 @default.
- W4380714525 hasConcept C41008148 @default.
- W4380714525 hasConcept C51432778 @default.
- W4380714525 hasConcept C54197355 @default.
- W4380714525 hasConcept C71924100 @default.
- W4380714525 hasConcept C76155785 @default.
- W4380714525 hasConcept C99498987 @default.
- W4380714525 hasConceptScore W4380714525C11413529 @default.
- W4380714525 hasConceptScore W4380714525C115961682 @default.
- W4380714525 hasConceptScore W4380714525C126838900 @default.
- W4380714525 hasConceptScore W4380714525C153180895 @default.
- W4380714525 hasConceptScore W4380714525C154945302 @default.
- W4380714525 hasConceptScore W4380714525C163294075 @default.
- W4380714525 hasConceptScore W4380714525C183115368 @default.
- W4380714525 hasConceptScore W4380714525C185142706 @default.
- W4380714525 hasConceptScore W4380714525C2776182073 @default.
- W4380714525 hasConceptScore W4380714525C28490314 @default.
- W4380714525 hasConceptScore W4380714525C33378366 @default.
- W4380714525 hasConceptScore W4380714525C41008148 @default.
- W4380714525 hasConceptScore W4380714525C51432778 @default.
- W4380714525 hasConceptScore W4380714525C54197355 @default.
- W4380714525 hasConceptScore W4380714525C71924100 @default.
- W4380714525 hasConceptScore W4380714525C76155785 @default.
- W4380714525 hasConceptScore W4380714525C99498987 @default.
- W4380714525 hasLocation W43807145251 @default.
- W4380714525 hasOpenAccess W4380714525 @default.
- W4380714525 hasPrimaryLocation W43807145251 @default.
- W4380714525 hasRelatedWork W1548707046 @default.
- W4380714525 hasRelatedWork W2049954146 @default.
- W4380714525 hasRelatedWork W2068198776 @default.
- W4380714525 hasRelatedWork W2111712073 @default.
- W4380714525 hasRelatedWork W2153269864 @default.
- W4380714525 hasRelatedWork W2290075840 @default.
- W4380714525 hasRelatedWork W2290466121 @default.
- W4380714525 hasRelatedWork W2522007883 @default.
- W4380714525 hasRelatedWork W2636483419 @default.
- W4380714525 hasRelatedWork W2921997986 @default.
- W4380714525 isParatext "false" @default.
- W4380714525 isRetracted "false" @default.
- W4380714525 workType "article" @default.