FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200345197> ?p ?o ?g. }

• W3200345197 abstract "Automatic lyrics transcription (ALT), which can be regarded as automatic speech recognition (ASR) on singing voice, is an interesting and practical topic in academia and industry. ALT has not been well developed mainly due to the dearth of paired singing voice and lyrics datasets for model training. Considering that there is a large amount of ASR training data, a straightforward method is to leverage ASR data to enhance ALT training. However, the improvement is marginal when training the ALT system directly with ASR data, because of the gap between the singing voice and standard speech data which is rooted in music-specific acoustic characteristics in singing voice. In this paper, we propose PDAugment, a data augmentation method that adjusts pitch and duration of speech at syllable level under the guidance of music scores to help ALT training. Specifically, we adjust the pitch and duration of each syllable in natural speech to those of the corresponding note extracted from music scores, so as to narrow the gap between natural speech and singing voice. Experiments on DSing30 and Dali corpus show that the ALT system equipped with our PDAugment outperforms previous state-of-the-art systems by 5.9% and 18.1% WERs respectively, demonstrating the effectiveness of PDAugment for ALT." @default.
• W3200345197 created "2021-09-27" @default.
• W3200345197 creator A5004649800 @default.
• W3200345197 creator A5018286848 @default.
• W3200345197 creator A5020025718 @default.
• W3200345197 creator A5026251593 @default.
• W3200345197 creator A5028225823 @default.
• W3200345197 creator A5034855502 @default.
• W3200345197 creator A5088711291 @default.
• W3200345197 date "2021-09-16" @default.
• W3200345197 modified "2023-10-16" @default.
• W3200345197 title "PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription" @default.
• W3200345197 cites W112239495 @default.
• W3200345197 cites W1494198834 @default.
• W3200345197 cites W1522301498 @default.
• W3200345197 cites W1585181552 @default.
• W3200345197 cites W182406043 @default.
• W3200345197 cites W1828163288 @default.
• W3200345197 cites W2059239154 @default.
• W3200345197 cites W2101927329 @default.
• W3200345197 cites W2127141656 @default.
• W3200345197 cites W2144731719 @default.
• W3200345197 cites W2164282073 @default.
• W3200345197 cites W2193413348 @default.
• W3200345197 cites W2327501763 @default.
• W3200345197 cites W2395129396 @default.
• W3200345197 cites W2471520273 @default.
• W3200345197 cites W2577008904 @default.
• W3200345197 cites W2747874407 @default.
• W3200345197 cites W2795935804 @default.
• W3200345197 cites W2889429804 @default.
• W3200345197 cites W2903006902 @default.
• W3200345197 cites W2936774411 @default.
• W3200345197 cites W2963403868 @default.
• W3200345197 cites W2964150074 @default.
• W3200345197 cites W2973071600 @default.
• W3200345197 cites W3015315843 @default.
• W3200345197 cites W3015927303 @default.
• W3200345197 cites W3016010032 @default.
• W3200345197 cites W3025165719 @default.
• W3200345197 cites W3081416955 @default.
• W3200345197 cites W3087621439 @default.
• W3200345197 cites W3090751054 @default.
• W3200345197 cites W3095189764 @default.
• W3200345197 cites W3111801244 @default.
• W3200345197 cites W3116834994 @default.
• W3200345197 cites W3132121394 @default.
• W3200345197 cites W3175871055 @default.
• W3200345197 cites W2293949002 @default.
• W3200345197 doi "https://doi.org/10.48550/arxiv.2109.07940" @default.
• W3200345197 hasPublicationYear "2021" @default.
• W3200345197 type Work @default.
• W3200345197 sameAs 3200345197 @default.
• W3200345197 citedByCount "0" @default.
• W3200345197 crossrefType "posted-content" @default.
• W3200345197 hasAuthorship W3200345197A5004649800 @default.
• W3200345197 hasAuthorship W3200345197A5018286848 @default.
• W3200345197 hasAuthorship W3200345197A5020025718 @default.
• W3200345197 hasAuthorship W3200345197A5026251593 @default.
• W3200345197 hasAuthorship W3200345197A5028225823 @default.
• W3200345197 hasAuthorship W3200345197A5034855502 @default.
• W3200345197 hasAuthorship W3200345197A5088711291 @default.
• W3200345197 hasBestOaLocation W32003451971 @default.
• W3200345197 hasConcept C109089402 @default.
• W3200345197 hasConcept C112758219 @default.
• W3200345197 hasConcept C121332964 @default.
• W3200345197 hasConcept C138885662 @default.
• W3200345197 hasConcept C153083717 @default.
• W3200345197 hasConcept C154945302 @default.
• W3200345197 hasConcept C166957645 @default.
• W3200345197 hasConcept C179926584 @default.
• W3200345197 hasConcept C204321447 @default.
• W3200345197 hasConcept C24890656 @default.
• W3200345197 hasConcept C2776436406 @default.
• W3200345197 hasConcept C2776608160 @default.
• W3200345197 hasConcept C28490314 @default.
• W3200345197 hasConcept C41008148 @default.
• W3200345197 hasConcept C41895202 @default.
• W3200345197 hasConcept C44819458 @default.
• W3200345197 hasConcept C95457728 @default.
• W3200345197 hasConceptScore W3200345197C109089402 @default.
• W3200345197 hasConceptScore W3200345197C112758219 @default.
• W3200345197 hasConceptScore W3200345197C121332964 @default.
• W3200345197 hasConceptScore W3200345197C138885662 @default.
• W3200345197 hasConceptScore W3200345197C153083717 @default.
• W3200345197 hasConceptScore W3200345197C154945302 @default.
• W3200345197 hasConceptScore W3200345197C166957645 @default.
• W3200345197 hasConceptScore W3200345197C179926584 @default.
• W3200345197 hasConceptScore W3200345197C204321447 @default.
• W3200345197 hasConceptScore W3200345197C24890656 @default.
• W3200345197 hasConceptScore W3200345197C2776436406 @default.
• W3200345197 hasConceptScore W3200345197C2776608160 @default.
• W3200345197 hasConceptScore W3200345197C28490314 @default.
• W3200345197 hasConceptScore W3200345197C41008148 @default.
• W3200345197 hasConceptScore W3200345197C41895202 @default.
• W3200345197 hasConceptScore W3200345197C44819458 @default.
• W3200345197 hasConceptScore W3200345197C95457728 @default.
• W3200345197 hasLocation W32003451971 @default.
• W3200345197 hasOpenAccess W3200345197 @default.
• W3200345197 hasPrimaryLocation W32003451971 @default.

• next