FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090224340> ?p ?o ?g. }

• W3090224340 abstract "We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation. Our study first investigates offline utterance-wise speaker separation and then extends to block-online continuous speech separation (CSS). Assuming a fixed array geometry between training and testing, we train deep neural networks (DNN) to predict the real and imaginary (RI) components of target speech at a reference microphone from the RI components of multiple microphones. We then integrate multi-microphone complex spectral mapping with minimum variance distortionless response (MVDR) beamforming and post-filtering to further improve separation, and combine it with frame-level speaker counting for block-online CSS. Although our system is trained on simulated room impulse responses (RIR) based on a fixed number of microphones arranged in a given geometry, it generalizes well to a real array with the same geometry. State-of-the-art separation performance is obtained on the simulated two-talker SMS-WSJ corpus and the real-recorded LibriCSS dataset." @default.
• W3090224340 created "2020-10-08" @default.
• W3090224340 creator A5022772351 @default.
• W3090224340 creator A5051837453 @default.
• W3090224340 creator A5062250845 @default.
• W3090224340 date "2020-10-04" @default.
• W3090224340 modified "2023-09-25" @default.
• W3090224340 title "Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation" @default.
• W3090224340 cites W1552314771 @default.
• W3090224340 cites W1901129140 @default.
• W3090224340 cites W2221409856 @default.
• W3090224340 cites W2288645994 @default.
• W3090224340 cites W2289480995 @default.
• W3090224340 cites W2291877678 @default.
• W3090224340 cites W2398972335 @default.
• W3090224340 cites W2460742184 @default.
• W3090224340 cites W2516001803 @default.
• W3090224340 cites W2559809918 @default.
• W3090224340 cites W2568308529 @default.
• W3090224340 cites W2701869962 @default.
• W3090224340 cites W2734774145 @default.
• W3090224340 cites W2792764867 @default.
• W3090224340 cites W2803322398 @default.
• W3090224340 cites W2810934215 @default.
• W3090224340 cites W2885219692 @default.
• W3090224340 cites W2892163332 @default.
• W3090224340 cites W2897977894 @default.
• W3090224340 cites W2900893004 @default.
• W3090224340 cites W2938386503 @default.
• W3090224340 cites W2945191446 @default.
• W3090224340 cites W2952218014 @default.
• W3090224340 cites W2962780374 @default.
• W3090224340 cites W2962866211 @default.
• W3090224340 cites W2963317762 @default.
• W3090224340 cites W2963446712 @default.
• W3090224340 cites W2963452667 @default.
• W3090224340 cites W2964058413 @default.
• W3090224340 cites W2972460025 @default.
• W3090224340 cites W2972992323 @default.
• W3090224340 cites W2982456909 @default.
• W3090224340 cites W2991361823 @default.
• W3090224340 cites W2992632249 @default.
• W3090224340 cites W3004309045 @default.
• W3090224340 cites W3007256793 @default.
• W3090224340 cites W3008880747 @default.
• W3090224340 cites W3009032512 @default.
• W3090224340 cites W3015199127 @default.
• W3090224340 cites W3015372568 @default.
• W3090224340 cites W3015679215 @default.
• W3090224340 cites W3015788098 @default.
• W3090224340 cites W3015843733 @default.
• W3090224340 cites W3016094953 @default.
• W3090224340 cites W3016232124 @default.
• W3090224340 cites W3016257794 @default.
• W3090224340 cites W3021208339 @default.
• W3090224340 cites W3032514799 @default.
• W3090224340 cites W3032969657 @default.
• W3090224340 cites W3048833027 @default.
• W3090224340 cites W3049380552 @default.
• W3090224340 cites W3086154751 @default.
• W3090224340 cites W3099177480 @default.
• W3090224340 cites W3123318516 @default.
• W3090224340 cites W3151596526 @default.
• W3090224340 doi "https://doi.org/10.48550/arxiv.2010.01703" @default.
• W3090224340 hasPublicationYear "2020" @default.
• W3090224340 type Work @default.
• W3090224340 sameAs 3090224340 @default.
• W3090224340 citedByCount "0" @default.
• W3090224340 crossrefType "posted-content" @default.
• W3090224340 hasAuthorship W3090224340A5022772351 @default.
• W3090224340 hasAuthorship W3090224340A5051837453 @default.
• W3090224340 hasAuthorship W3090224340A5062250845 @default.
• W3090224340 hasBestOaLocation W30902243401 @default.
• W3090224340 hasConcept C119857082 @default.
• W3090224340 hasConcept C121332964 @default.
• W3090224340 hasConcept C134306372 @default.
• W3090224340 hasConcept C154945302 @default.
• W3090224340 hasConcept C24890656 @default.
• W3090224340 hasConcept C2524010 @default.
• W3090224340 hasConcept C2776061190 @default.
• W3090224340 hasConcept C2776864781 @default.
• W3090224340 hasConcept C2777210771 @default.
• W3090224340 hasConcept C2778263558 @default.
• W3090224340 hasConcept C2778806681 @default.
• W3090224340 hasConcept C28490314 @default.
• W3090224340 hasConcept C33923547 @default.
• W3090224340 hasConcept C41008148 @default.
• W3090224340 hasConcept C50644808 @default.
• W3090224340 hasConcept C54197355 @default.
• W3090224340 hasConcept C68115822 @default.
• W3090224340 hasConcept C72279823 @default.
• W3090224340 hasConcept C76155785 @default.
• W3090224340 hasConceptScore W3090224340C119857082 @default.
• W3090224340 hasConceptScore W3090224340C121332964 @default.
• W3090224340 hasConceptScore W3090224340C134306372 @default.
• W3090224340 hasConceptScore W3090224340C154945302 @default.
• W3090224340 hasConceptScore W3090224340C24890656 @default.
• W3090224340 hasConceptScore W3090224340C2524010 @default.
• W3090224340 hasConceptScore W3090224340C2776061190 @default.
• W3090224340 hasConceptScore W3090224340C2776864781 @default.

• next