Statements (33)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:technology
|
| gptkbp:challenge |
accent variation
background noise speaker variability low-quality audio |
| gptkbp:field |
natural language processing
computational linguistics speech processing |
| https://www.w3.org/2000/01/rdf-schema#label |
Automatic Speech Alignment
|
| gptkbp:input |
audio recordings
transcript |
| gptkbp:method |
gptkb:Hidden_Markov_Model
gptkb:Deep_Neural_Network Dynamic Time Warping |
| gptkbp:output |
phoneme boundaries
time-aligned transcript word boundaries |
| gptkbp:relatedTo |
gptkb:Automatic_Speech_Recognition
Phonetic Alignment Speech Segmentation |
| gptkbp:software |
gptkb:Gentle
Montreal Forced Aligner Penn Forced Aligner WebMAUS |
| gptkbp:usedFor |
phonetic transcription
aligning audio with text forced alignment |
| gptkbp:usedIn |
speech recognition
linguistic theory language documentation corpus annotation |
| gptkbp:bfsParent |
gptkb:Adobe_Audition_24.2
|
| gptkbp:bfsLayer |
7
|