Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312698052> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4312698052 endingPage "598" @default.
- W4312698052 startingPage "585" @default.
- W4312698052 abstract "AbstractPhoneme segmentation is important for many healthcare applications, such as the diagnosis and monitoring of children with speech sound disorders (SSDs). This is usually addressed by performing forced alignment (FA), which essentially annotates an audio file to provide information on what has been uttered and where. While many FA tools exist, very few can work automatically without the assistance of a transcription. This work aims at providing a novel text-independent FA tool by using two models, namely wav2vec 2.0 and an unsupervised segmentor known as UnsupSeg. To provide labels to the segments, the class regions that are obtained by nearest-neighbour classification with wav2vec 2.0 labels pre-CTC collapse as the reference points. Maximal overlap between the class regions and the segments determines class label. Additional post-processing steps, such as over-fitting cleaning and application of voice activity detection, are also performed to further improve the segmentation performance. All the models used to create the tool are self-supervised, and thus can leverage great amounts of unlabelled data to reduce the need for labelled data. When evaluated on the TIMIT dataset, our implementation achieved a harmonic mean score of 76.88%, competitive against other alternatives.KeywordsForced alignmentPhoneme segmentationTransformerSelf-supervised learningConnectionist temporal classificationVoice activity detectorSpeech sound disorderSpeech processingDeep learning" @default.
- W4312698052 created "2023-01-05" @default.
- W4312698052 creator A5004852178 @default.
- W4312698052 creator A5068506332 @default.
- W4312698052 creator A5068550413 @default.
- W4312698052 creator A5073597798 @default.
- W4312698052 date "2022-01-01" @default.
- W4312698052 modified "2023-09-26" @default.
- W4312698052 title "A Text-Independent Forced Alignment Method for Automatic Phoneme Segmentation" @default.
- W4312698052 cites W1548813916 @default.
- W4312698052 cites W2017724783 @default.
- W4312698052 cites W2079735306 @default.
- W4312698052 cites W2090351498 @default.
- W4312698052 cites W2131774270 @default.
- W4312698052 cites W2587378950 @default.
- W4312698052 cites W2592580733 @default.
- W4312698052 cites W2616818472 @default.
- W4312698052 cites W2833335833 @default.
- W4312698052 cites W2890709906 @default.
- W4312698052 cites W2979803276 @default.
- W4312698052 cites W3006094508 @default.
- W4312698052 cites W3096656254 @default.
- W4312698052 cites W3207272747 @default.
- W4312698052 cites W4251756105 @default.
- W4312698052 doi "https://doi.org/10.1007/978-3-031-22695-3_41" @default.
- W4312698052 hasPublicationYear "2022" @default.
- W4312698052 type Work @default.
- W4312698052 citedByCount "0" @default.
- W4312698052 crossrefType "book-chapter" @default.
- W4312698052 hasAuthorship W4312698052A5004852178 @default.
- W4312698052 hasAuthorship W4312698052A5068506332 @default.
- W4312698052 hasAuthorship W4312698052A5068550413 @default.
- W4312698052 hasAuthorship W4312698052A5073597798 @default.
- W4312698052 hasConcept C119857082 @default.
- W4312698052 hasConcept C153083717 @default.
- W4312698052 hasConcept C153180895 @default.
- W4312698052 hasConcept C154945302 @default.
- W4312698052 hasConcept C23224414 @default.
- W4312698052 hasConcept C2777212361 @default.
- W4312698052 hasConcept C2778724510 @default.
- W4312698052 hasConcept C28490314 @default.
- W4312698052 hasConcept C41008148 @default.
- W4312698052 hasConcept C89600930 @default.
- W4312698052 hasConceptScore W4312698052C119857082 @default.
- W4312698052 hasConceptScore W4312698052C153083717 @default.
- W4312698052 hasConceptScore W4312698052C153180895 @default.
- W4312698052 hasConceptScore W4312698052C154945302 @default.
- W4312698052 hasConceptScore W4312698052C23224414 @default.
- W4312698052 hasConceptScore W4312698052C2777212361 @default.
- W4312698052 hasConceptScore W4312698052C2778724510 @default.
- W4312698052 hasConceptScore W4312698052C28490314 @default.
- W4312698052 hasConceptScore W4312698052C41008148 @default.
- W4312698052 hasConceptScore W4312698052C89600930 @default.
- W4312698052 hasLocation W43126980521 @default.
- W4312698052 hasOpenAccess W4312698052 @default.
- W4312698052 hasPrimaryLocation W43126980521 @default.
- W4312698052 hasRelatedWork W1507687735 @default.
- W4312698052 hasRelatedWork W177166743 @default.
- W4312698052 hasRelatedWork W1965276979 @default.
- W4312698052 hasRelatedWork W1994694193 @default.
- W4312698052 hasRelatedWork W2005708641 @default.
- W4312698052 hasRelatedWork W2008638795 @default.
- W4312698052 hasRelatedWork W2051178523 @default.
- W4312698052 hasRelatedWork W2119232697 @default.
- W4312698052 hasRelatedWork W2155033763 @default.
- W4312698052 hasRelatedWork W2166866311 @default.
- W4312698052 isParatext "false" @default.
- W4312698052 isRetracted "false" @default.
- W4312698052 workType "book-chapter" @default.