FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193633919> ?p ?o ?g. }

• W3193633919 abstract "A promising approach for speech dereverberation is based on supervised learning, where a deep neural network (DNN) is trained to predict the direct sound from noisy-reverberant speech. This data-driven approach is based on leveraging prior knowledge of clean speech patterns and seldom explicitly exploits the linear-filter structure in reverberation, i.e., that reverberation results from a linear convolution between a room impulse response (RIR) and a dry source signal. In this work, we propose to exploit this linear-filter structure within a deep learning based monaural speech dereverberation framework. The key idea is to first estimate the direct-path signal of the target speaker using a DNN and then identify signals that are decayed and delayed copies of the estimated direct-path signal, as these can be reliably considered as reverberation. They can be either directly removed for dereverberation, or used as extra features for another DNN to perform better dereverberation. To identify the copies, we estimate the underlying filter (or RIR) by efficiently solving a linear regression problem per frequency in the time-frequency domain. We then modify the proposed algorithm for speaker separation in reverberant and noisy-reverberant conditions. State-of-the-art speech dereverberation and speaker separation results are obtained on the REVERB, SMS-WSJ, and WHAMR! datasets." @default.
• W3193633919 created "2021-08-30" @default.
• W3193633919 creator A5022772351 @default.
• W3193633919 creator A5076453358 @default.
• W3193633919 creator A5086940921 @default.
• W3193633919 date "2021-08-16" @default.
• W3193633919 modified "2023-09-27" @default.
• W3193633919 title "Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation" @default.
• W3193633919 cites W1482149378 @default.
• W3193633919 cites W1524333225 @default.
• W3193633919 cites W1555217905 @default.
• W3193633919 cites W1901129140 @default.
• W3193633919 cites W1973669708 @default.
• W3193633919 cites W2006129368 @default.
• W3193633919 cites W2023331723 @default.
• W3193633919 cites W2035576074 @default.
• W3193633919 cites W2045043668 @default.
• W3193633919 cites W2069681747 @default.
• W3193633919 cites W2127851351 @default.
• W3193633919 cites W2141998673 @default.
• W3193633919 cites W2156676906 @default.
• W3193633919 cites W2161784349 @default.
• W3193633919 cites W2161804069 @default.
• W3193633919 cites W2164502538 @default.
• W3193633919 cites W2168610508 @default.
• W3193633919 cites W2221409856 @default.
• W3193633919 cites W2242685705 @default.
• W3193633919 cites W2291877678 @default.
• W3193633919 cites W2304609584 @default.
• W3193633919 cites W2568308529 @default.
• W3193633919 cites W2698117193 @default.
• W3193633919 cites W2734774145 @default.
• W3193633919 cites W2747732471 @default.
• W3193633919 cites W2763188033 @default.
• W3193633919 cites W2774389566 @default.
• W3193633919 cites W2791524682 @default.
• W3193633919 cites W2792764867 @default.
• W3193633919 cites W2884797218 @default.
• W3193633919 cites W2889540509 @default.
• W3193633919 cites W2899625056 @default.
• W3193633919 cites W2900212944 @default.
• W3193633919 cites W2939777271 @default.
• W3193633919 cites W2952218014 @default.
• W3193633919 cites W2962715207 @default.
• W3193633919 cites W2962866211 @default.
• W3193633919 cites W2962905190 @default.
• W3193633919 cites W2963197115 @default.
• W3193633919 cites W2963403868 @default.
• W3193633919 cites W2963446712 @default.
• W3193633919 cites W2963941778 @default.
• W3193633919 cites W2972460025 @default.
• W3193633919 cites W2972541922 @default.
• W3193633919 cites W2982456909 @default.
• W3193633919 cites W2998657200 @default.
• W3193633919 cites W3007256793 @default.
• W3193633919 cites W3008880747 @default.
• W3193633919 cites W3015191643 @default.
• W3193633919 cites W3015199127 @default.
• W3193633919 cites W3015679215 @default.
• W3193633919 cites W3026111682 @default.
• W3193633919 cites W3032514799 @default.
• W3193633919 cites W3082256262 @default.
• W3193633919 cites W3086154751 @default.
• W3193633919 cites W3096073522 @default.
• W3193633919 cites W3111051109 @default.
• W3193633919 cites W3163652268 @default.
• W3193633919 cites W3171278394 @default.
• W3193633919 doi "https://doi.org/10.48550/arxiv.2108.07376" @default.
• W3193633919 hasPublicationYear "2021" @default.
• W3193633919 type Work @default.
• W3193633919 sameAs 3193633919 @default.
• W3193633919 citedByCount "2" @default.
• W3193633919 countsByYear W31936339192021 @default.
• W3193633919 countsByYear W31936339192022 @default.
• W3193633919 crossrefType "posted-content" @default.
• W3193633919 hasAuthorship W3193633919A5022772351 @default.
• W3193633919 hasAuthorship W3193633919A5076453358 @default.
• W3193633919 hasAuthorship W3193633919A5086940921 @default.
• W3193633919 hasBestOaLocation W31936339191 @default.
• W3193633919 hasConcept C102894143 @default.
• W3193633919 hasConcept C106131492 @default.
• W3193633919 hasConcept C121332964 @default.
• W3193633919 hasConcept C131109320 @default.
• W3193633919 hasConcept C134306372 @default.
• W3193633919 hasConcept C154945302 @default.
• W3193633919 hasConcept C199360897 @default.
• W3193633919 hasConcept C24890656 @default.
• W3193633919 hasConcept C2779843651 @default.
• W3193633919 hasConcept C28490314 @default.
• W3193633919 hasConcept C31972630 @default.
• W3193633919 hasConcept C33923547 @default.
• W3193633919 hasConcept C41008148 @default.
• W3193633919 hasConcept C45347329 @default.
• W3193633919 hasConcept C50644808 @default.
• W3193633919 hasConcept C72279823 @default.
• W3193633919 hasConcept C95851461 @default.
• W3193633919 hasConceptScore W3193633919C102894143 @default.
• W3193633919 hasConceptScore W3193633919C106131492 @default.
• W3193633919 hasConceptScore W3193633919C121332964 @default.
• W3193633919 hasConceptScore W3193633919C131109320 @default.

• next