Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288889670> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4288889670 abstract "The task of phone-to-audio alignment has many applications in speech research. Here we introduce two Wav2Vec2-based models for both text-dependent and text-independent phone-to-audio alignment. The proposed Wav2Vec2-FS, a semi-supervised model, directly learns phone-to-audio alignment through contrastive learning and a forward sum loss, and can be coupled with a pretrained phone recognizer to achieve text-independent alignment. The other model, Wav2Vec2-FC, is a frame classification model trained on forced aligned labels that can both perform forced alignment and text-independent segmentation. Evaluation results suggest that both proposed methods, even when transcriptions are not available, generate highly close results to existing forced alignment tools. Our work presents a neural pipeline of fully automated phone-to-audio alignment. Code and pretrained models are available at https://github.com/lingjzhu/charsiu." @default.
- W4288889670 created "2022-07-31" @default.
- W4288889670 creator A5032686951 @default.
- W4288889670 creator A5046126345 @default.
- W4288889670 creator A5074734978 @default.
- W4288889670 date "2021-10-07" @default.
- W4288889670 modified "2023-09-29" @default.
- W4288889670 title "Phone-to-audio alignment without text: A Semi-supervised Approach" @default.
- W4288889670 doi "https://doi.org/10.48550/arxiv.2110.03876" @default.
- W4288889670 hasPublicationYear "2021" @default.
- W4288889670 type Work @default.
- W4288889670 citedByCount "0" @default.
- W4288889670 crossrefType "posted-content" @default.
- W4288889670 hasAuthorship W4288889670A5032686951 @default.
- W4288889670 hasAuthorship W4288889670A5046126345 @default.
- W4288889670 hasAuthorship W4288889670A5074734978 @default.
- W4288889670 hasBestOaLocation W42888896701 @default.
- W4288889670 hasConcept C126042441 @default.
- W4288889670 hasConcept C138885662 @default.
- W4288889670 hasConcept C153180895 @default.
- W4288889670 hasConcept C154945302 @default.
- W4288889670 hasConcept C162324750 @default.
- W4288889670 hasConcept C177264268 @default.
- W4288889670 hasConcept C187736073 @default.
- W4288889670 hasConcept C199360897 @default.
- W4288889670 hasConcept C204321447 @default.
- W4288889670 hasConcept C2776760102 @default.
- W4288889670 hasConcept C2778707766 @default.
- W4288889670 hasConcept C2780451532 @default.
- W4288889670 hasConcept C28490314 @default.
- W4288889670 hasConcept C41008148 @default.
- W4288889670 hasConcept C41895202 @default.
- W4288889670 hasConcept C43521106 @default.
- W4288889670 hasConcept C76155785 @default.
- W4288889670 hasConcept C89600930 @default.
- W4288889670 hasConceptScore W4288889670C126042441 @default.
- W4288889670 hasConceptScore W4288889670C138885662 @default.
- W4288889670 hasConceptScore W4288889670C153180895 @default.
- W4288889670 hasConceptScore W4288889670C154945302 @default.
- W4288889670 hasConceptScore W4288889670C162324750 @default.
- W4288889670 hasConceptScore W4288889670C177264268 @default.
- W4288889670 hasConceptScore W4288889670C187736073 @default.
- W4288889670 hasConceptScore W4288889670C199360897 @default.
- W4288889670 hasConceptScore W4288889670C204321447 @default.
- W4288889670 hasConceptScore W4288889670C2776760102 @default.
- W4288889670 hasConceptScore W4288889670C2778707766 @default.
- W4288889670 hasConceptScore W4288889670C2780451532 @default.
- W4288889670 hasConceptScore W4288889670C28490314 @default.
- W4288889670 hasConceptScore W4288889670C41008148 @default.
- W4288889670 hasConceptScore W4288889670C41895202 @default.
- W4288889670 hasConceptScore W4288889670C43521106 @default.
- W4288889670 hasConceptScore W4288889670C76155785 @default.
- W4288889670 hasConceptScore W4288889670C89600930 @default.
- W4288889670 hasLocation W42888896701 @default.
- W4288889670 hasOpenAccess W4288889670 @default.
- W4288889670 hasPrimaryLocation W42888896701 @default.
- W4288889670 hasRelatedWork W10183233 @default.
- W4288889670 hasRelatedWork W11012074 @default.
- W4288889670 hasRelatedWork W11209375 @default.
- W4288889670 hasRelatedWork W13423774 @default.
- W4288889670 hasRelatedWork W14712889 @default.
- W4288889670 hasRelatedWork W1697457 @default.
- W4288889670 hasRelatedWork W2218946 @default.
- W4288889670 hasRelatedWork W2864082 @default.
- W4288889670 hasRelatedWork W5192282 @default.
- W4288889670 hasRelatedWork W5683847 @default.
- W4288889670 isParatext "false" @default.
- W4288889670 isRetracted "false" @default.
- W4288889670 workType "article" @default.