Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167770415> ?p ?o ?g. }
- W3167770415 abstract "Speaker extraction algorithm emulates human's ability of selective attention to extract the target speaker's speech from a multi-talker scenario. It requires an auxiliary stimulus to form the top-down attention towards the target speaker. It has been well studied to use a reference speech as the auxiliary stimulus. Visual cues also serve as an informative reference for human listening. They are particularly useful in the presence of acoustic noise and interference speakers. We believe that the temporal synchronization between speech and its accompanying lip motion is a direct and dominant audio-visual cue. In this work, we aim to emulate human's ability of visual attention for speaker extraction based on speech-lip synchronization. We propose a self-supervised pre-training strategy, to exploit the speech-lip synchronization in a multi-talker scenario. We transfer the knowledge from the pre-trained model to a speaker extraction network. We show that the proposed speaker extraction network outperforms various competitive baselines in terms of signal quality and perceptual evaluation, achieving state-of-the-art performance." @default.
- W3167770415 created "2021-06-22" @default.
- W3167770415 creator A5026034735 @default.
- W3167770415 creator A5032690182 @default.
- W3167770415 creator A5060530570 @default.
- W3167770415 creator A5080053477 @default.
- W3167770415 date "2021-06-14" @default.
- W3167770415 modified "2023-09-27" @default.
- W3167770415 title "Selective Hearing through Lip-reading" @default.
- W3167770415 cites W1482149378 @default.
- W3167770415 cites W1552314771 @default.
- W3167770415 cites W1932061758 @default.
- W3167770415 cites W1966823466 @default.
- W3167770415 cites W1991139021 @default.
- W3167770415 cites W2015143272 @default.
- W3167770415 cites W2020141429 @default.
- W3167770415 cites W2029199293 @default.
- W3167770415 cites W2069681747 @default.
- W3167770415 cites W2081144555 @default.
- W3167770415 cites W2103104224 @default.
- W3167770415 cites W2107938580 @default.
- W3167770415 cites W2141411743 @default.
- W3167770415 cites W2147455188 @default.
- W3167770415 cites W2152790380 @default.
- W3167770415 cites W2221409856 @default.
- W3167770415 cites W2333091651 @default.
- W3167770415 cites W2519091744 @default.
- W3167770415 cites W2521686623 @default.
- W3167770415 cites W2587150483 @default.
- W3167770415 cites W2594690981 @default.
- W3167770415 cites W2604379605 @default.
- W3167770415 cites W2734774145 @default.
- W3167770415 cites W2741151796 @default.
- W3167770415 cites W2787692317 @default.
- W3167770415 cites W2800022361 @default.
- W3167770415 cites W2808631503 @default.
- W3167770415 cites W2888968865 @default.
- W3167770415 cites W2889418727 @default.
- W3167770415 cites W2890952074 @default.
- W3167770415 cites W2891205112 @default.
- W3167770415 cites W2891833136 @default.
- W3167770415 cites W2900292050 @default.
- W3167770415 cites W2924115626 @default.
- W3167770415 cites W2938646939 @default.
- W3167770415 cites W2950864153 @default.
- W3167770415 cites W2951130829 @default.
- W3167770415 cites W2962788625 @default.
- W3167770415 cites W2962960500 @default.
- W3167770415 cites W2963082324 @default.
- W3167770415 cites W2963103134 @default.
- W3167770415 cites W2963452667 @default.
- W3167770415 cites W2963528589 @default.
- W3167770415 cites W2964121744 @default.
- W3167770415 cites W2964171275 @default.
- W3167770415 cites W2964283370 @default.
- W3167770415 cites W2972460025 @default.
- W3167770415 cites W2972513594 @default.
- W3167770415 cites W2972568703 @default.
- W3167770415 cites W2973054998 @default.
- W3167770415 cites W2973062255 @default.
- W3167770415 cites W3008400075 @default.
- W3167770415 cites W3008880747 @default.
- W3167770415 cites W3010457696 @default.
- W3167770415 cites W3015199127 @default.
- W3167770415 cites W3015445830 @default.
- W3167770415 cites W3015623828 @default.
- W3167770415 cites W3015636705 @default.
- W3167770415 cites W3024147341 @default.
- W3167770415 cites W3036438531 @default.
- W3167770415 cites W3095082129 @default.
- W3167770415 cites W3095379519 @default.
- W3167770415 cites W3096214032 @default.
- W3167770415 cites W3097653961 @default.
- W3167770415 cites W3097741049 @default.
- W3167770415 cites W3097829404 @default.
- W3167770415 cites W3103434036 @default.
- W3167770415 cites W3105928222 @default.
- W3167770415 cites W3116298410 @default.
- W3167770415 cites W3120774255 @default.
- W3167770415 cites W3123318516 @default.
- W3167770415 cites W3124666641 @default.
- W3167770415 cites W3148386121 @default.
- W3167770415 cites W3162534564 @default.
- W3167770415 cites W3163287738 @default.
- W3167770415 hasPublicationYear "2021" @default.
- W3167770415 type Work @default.
- W3167770415 sameAs 3167770415 @default.
- W3167770415 citedByCount "1" @default.
- W3167770415 countsByYear W31677704152021 @default.
- W3167770415 crossrefType "posted-content" @default.
- W3167770415 hasAuthorship W3167770415A5026034735 @default.
- W3167770415 hasAuthorship W3167770415A5032690182 @default.
- W3167770415 hasAuthorship W3167770415A5060530570 @default.
- W3167770415 hasAuthorship W3167770415A5080053477 @default.
- W3167770415 hasConcept C127162648 @default.
- W3167770415 hasConcept C154945302 @default.
- W3167770415 hasConcept C15744967 @default.
- W3167770415 hasConcept C169760540 @default.
- W3167770415 hasConcept C177291462 @default.
- W3167770415 hasConcept C204201278 @default.