Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378465128> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4378465128 abstract "Audio-visual speech enhancement (AV-SE) aims to enhance degraded speech along with extra visual information such as lip videos, and has been shown to be more effective than audio-only speech enhancement. This paper proposes further incorporating ultrasound tongue images to improve lip-based AV-SE systems' performance. Knowledge distillation is employed at the training stage to address the challenge of acquiring ultrasound tongue images during inference, enabling an audio-lip speech enhancement student model to learn from a pre-trained audio-lip-tongue speech enhancement teacher model. Experimental results demonstrate significant improvements in the quality and intelligibility of the speech enhanced by the proposed method compared to the traditional audio-lip speech enhancement baselines. Further analysis using phone error rates (PER) of automatic speech recognition (ASR) shows that palatal and velar consonants benefit most from the introduction of ultrasound tongue images." @default.
- W4378465128 created "2023-05-27" @default.
- W4378465128 creator A5014746276 @default.
- W4378465128 creator A5059767940 @default.
- W4378465128 creator A5066498315 @default.
- W4378465128 date "2023-05-24" @default.
- W4378465128 modified "2023-09-26" @default.
- W4378465128 title "Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement through Knowledge Distillation" @default.
- W4378465128 doi "https://doi.org/10.48550/arxiv.2305.14933" @default.
- W4378465128 hasPublicationYear "2023" @default.
- W4378465128 type Work @default.
- W4378465128 citedByCount "0" @default.
- W4378465128 crossrefType "posted-content" @default.
- W4378465128 hasAuthorship W4378465128A5014746276 @default.
- W4378465128 hasAuthorship W4378465128A5059767940 @default.
- W4378465128 hasAuthorship W4378465128A5066498315 @default.
- W4378465128 hasBestOaLocation W43784651281 @default.
- W4378465128 hasConcept C111472728 @default.
- W4378465128 hasConcept C138885662 @default.
- W4378465128 hasConcept C142724271 @default.
- W4378465128 hasConcept C154945302 @default.
- W4378465128 hasConcept C163294075 @default.
- W4378465128 hasConcept C2776182073 @default.
- W4378465128 hasConcept C2776214188 @default.
- W4378465128 hasConcept C2778707766 @default.
- W4378465128 hasConcept C2779744641 @default.
- W4378465128 hasConcept C28490314 @default.
- W4378465128 hasConcept C41008148 @default.
- W4378465128 hasConcept C41895202 @default.
- W4378465128 hasConcept C60048801 @default.
- W4378465128 hasConcept C71924100 @default.
- W4378465128 hasConceptScore W4378465128C111472728 @default.
- W4378465128 hasConceptScore W4378465128C138885662 @default.
- W4378465128 hasConceptScore W4378465128C142724271 @default.
- W4378465128 hasConceptScore W4378465128C154945302 @default.
- W4378465128 hasConceptScore W4378465128C163294075 @default.
- W4378465128 hasConceptScore W4378465128C2776182073 @default.
- W4378465128 hasConceptScore W4378465128C2776214188 @default.
- W4378465128 hasConceptScore W4378465128C2778707766 @default.
- W4378465128 hasConceptScore W4378465128C2779744641 @default.
- W4378465128 hasConceptScore W4378465128C28490314 @default.
- W4378465128 hasConceptScore W4378465128C41008148 @default.
- W4378465128 hasConceptScore W4378465128C41895202 @default.
- W4378465128 hasConceptScore W4378465128C60048801 @default.
- W4378465128 hasConceptScore W4378465128C71924100 @default.
- W4378465128 hasLocation W43784651281 @default.
- W4378465128 hasOpenAccess W4378465128 @default.
- W4378465128 hasPrimaryLocation W43784651281 @default.
- W4378465128 hasRelatedWork W1986772939 @default.
- W4378465128 hasRelatedWork W2037635165 @default.
- W4378465128 hasRelatedWork W2063570496 @default.
- W4378465128 hasRelatedWork W2187949121 @default.
- W4378465128 hasRelatedWork W2403830142 @default.
- W4378465128 hasRelatedWork W2473013907 @default.
- W4378465128 hasRelatedWork W3129072390 @default.
- W4378465128 hasRelatedWork W4200562864 @default.
- W4378465128 hasRelatedWork W4221152531 @default.
- W4378465128 hasRelatedWork W4375869276 @default.
- W4378465128 isParatext "false" @default.
- W4378465128 isRetracted "false" @default.
- W4378465128 workType "article" @default.