Improving Text-Independent Forced Alignment to Support Speech-Language Pathologists with Phonetic Transcription
Ying Li, Bryce Johannas Wohlan, Duc-Son Pham, Kit Yan Chan, Roslyn Ward, Neville Hennessey, Tele Tan · 2023
Read Improving Text-Independent Forced Alignment to Support Speech-Language Pathologists with Phonetic Transcription by Ying Li, Bryce Johannas Wohlan, Duc-Son Pham, Kit Yan Chan, Roslyn Ward, Neville Hennessey, Tele Tan (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10747711.txt.
Description
Ying Li and co-authors improve speech sound alignment for clinicians in a 2023 paper. Phonetic transcription helps diagnose speech sound disorders, but it depends on the transcriber's ear and can carry bias. Forced alignment tools mark what was said and where, yet most need a hand written transcript first. Their model works with no transcript.
A pretrained wav2vec model splits speech into tokens and labels sounds on its own. An unsupervised tool sets sound boundaries, and extra cleaning steps sharpen the result. Scores on a normal speech set and a disorder speech set are competitive, they report. The method promises more objective assessment.
Catalog record
| CREATOR | Ying Li, Bryce Johannas Wohlan, Duc-Son Pham, Kit Yan Chan, Roslyn Ward, Neville Hennessey, Tele Tan |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |