Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361019596> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4361019596 abstract "Perceptually-inspired objective functions such as the perceptual evaluation of speech quality (PESQ), signal-to-distortion ratio (SDR), and short-time objective intelligibility (STOI), have recently been used to optimize performance of deep-learning-based speech enhancement algorithms. These objective functions, however, do not always strongly correlate with a listener's assessment of perceptual quality, so optimizing with these measures often results in poorer performance in real-world scenarios. In this work, we propose an attention-based enhancement approach that uses learned speech embedding vectors from a mean-opinion score (MOS) prediction model and a speech enhancement module to jointly enhance noisy speech. The MOS prediction model estimates the perceptual MOS of speech quality, as assessed by human listeners, directly from the audio signal. The enhancement module also employs a quantized language model that enforces spectral constraints for better speech realism and performance. We train the model using real-world noisy speech data that has been captured in everyday environments and test it using unseen corpora. The results show that our proposed approach significantly outperforms other approaches that are optimized with objective measures, where the predicted quality scores strongly correlate with human judgments." @default.
- W4361019596 created "2023-03-30" @default.
- W4361019596 creator A5024885435 @default.
- W4361019596 creator A5037914201 @default.
- W4361019596 date "2023-03-23" @default.
- W4361019596 modified "2023-10-17" @default.
- W4361019596 title "Attention-based Speech Enhancement Using Human Quality Perception Modelling" @default.
- W4361019596 doi "https://doi.org/10.48550/arxiv.2303.13685" @default.
- W4361019596 hasPublicationYear "2023" @default.
- W4361019596 type Work @default.
- W4361019596 citedByCount "0" @default.
- W4361019596 crossrefType "posted-content" @default.
- W4361019596 hasAuthorship W4361019596A5024885435 @default.
- W4361019596 hasAuthorship W4361019596A5037914201 @default.
- W4361019596 hasBestOaLocation W43610195961 @default.
- W4361019596 hasConcept C103734657 @default.
- W4361019596 hasConcept C108699837 @default.
- W4361019596 hasConcept C111472728 @default.
- W4361019596 hasConcept C119857082 @default.
- W4361019596 hasConcept C127413603 @default.
- W4361019596 hasConcept C138885662 @default.
- W4361019596 hasConcept C154945302 @default.
- W4361019596 hasConcept C15744967 @default.
- W4361019596 hasConcept C163294075 @default.
- W4361019596 hasConcept C169760540 @default.
- W4361019596 hasConcept C176217482 @default.
- W4361019596 hasConcept C204201278 @default.
- W4361019596 hasConcept C21547014 @default.
- W4361019596 hasConcept C26760741 @default.
- W4361019596 hasConcept C2776182073 @default.
- W4361019596 hasConcept C28490314 @default.
- W4361019596 hasConcept C41008148 @default.
- W4361019596 hasConcept C60048801 @default.
- W4361019596 hasConcept C61328038 @default.
- W4361019596 hasConcept C62897895 @default.
- W4361019596 hasConceptScore W4361019596C103734657 @default.
- W4361019596 hasConceptScore W4361019596C108699837 @default.
- W4361019596 hasConceptScore W4361019596C111472728 @default.
- W4361019596 hasConceptScore W4361019596C119857082 @default.
- W4361019596 hasConceptScore W4361019596C127413603 @default.
- W4361019596 hasConceptScore W4361019596C138885662 @default.
- W4361019596 hasConceptScore W4361019596C154945302 @default.
- W4361019596 hasConceptScore W4361019596C15744967 @default.
- W4361019596 hasConceptScore W4361019596C163294075 @default.
- W4361019596 hasConceptScore W4361019596C169760540 @default.
- W4361019596 hasConceptScore W4361019596C176217482 @default.
- W4361019596 hasConceptScore W4361019596C204201278 @default.
- W4361019596 hasConceptScore W4361019596C21547014 @default.
- W4361019596 hasConceptScore W4361019596C26760741 @default.
- W4361019596 hasConceptScore W4361019596C2776182073 @default.
- W4361019596 hasConceptScore W4361019596C28490314 @default.
- W4361019596 hasConceptScore W4361019596C41008148 @default.
- W4361019596 hasConceptScore W4361019596C60048801 @default.
- W4361019596 hasConceptScore W4361019596C61328038 @default.
- W4361019596 hasConceptScore W4361019596C62897895 @default.
- W4361019596 hasLocation W43610195961 @default.
- W4361019596 hasOpenAccess W4361019596 @default.
- W4361019596 hasPrimaryLocation W43610195961 @default.
- W4361019596 hasRelatedWork W1893647155 @default.
- W4361019596 hasRelatedWork W2048364231 @default.
- W4361019596 hasRelatedWork W2140344044 @default.
- W4361019596 hasRelatedWork W2140410589 @default.
- W4361019596 hasRelatedWork W2508873320 @default.
- W4361019596 hasRelatedWork W2542098180 @default.
- W4361019596 hasRelatedWork W2542497601 @default.
- W4361019596 hasRelatedWork W2993330232 @default.
- W4361019596 hasRelatedWork W4280635064 @default.
- W4361019596 hasRelatedWork W4361019596 @default.
- W4361019596 isParatext "false" @default.
- W4361019596 isRetracted "false" @default.
- W4361019596 workType "article" @default.