![]() ![]() Cite (Informal): The Post-Stroke Speech Transcription (PSST) Challenge (Gale et al., RaPID 2022) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: Code psst-challenge/psstbaseline Data = "The Post-Stroke Speech Transcription (, respectively.", ![]() In Proceedings of the RaPID Workshop - Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments - within the 13th Language Resources and Evaluation Conference, pages 41–55, Marseille, France. The Post-Stroke Speech Transcription (PSST) Challenge. Gale, Mikala Fleegle, Gerasimos Fergadiotis, and Steven Bedrick. Anthology ID: 2022.rapid-1.6 Volume: Proceedings of the RaPID Workshop - Resources and ProcessIng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments - within the 13th Language Resources and Evaluation Conference Month: June Year: 2022 Address: Marseille, France Venue: RaPID SIG: Publisher: European Language Resources Association Note: Pages: 41–55 Language: URL: DOI: Bibkey: gale-etal-2022-post Cite (ACL): Robert C. Challengers were unable to improve on the baseline algorithm however, using this algorithm with the improved transcripts from Task A resulted in 92.8% accuracy / 0.921 F1, a relative improvement of 2.8% and 3.3%, respectively. Task B approximated a downstream assessment task, asking challengers to identify whether each recording contained a correctly pronounced target word. The best model had a 9.9% FER / 20.0% PER, improving on our baseline by a relative 18% and 24%, respectively. Task A asked challengers to build an automatic speech recognizer (ASR) for phonemic transcription of the PSST samples, evaluated in terms of phoneme error rate (PER) as well as a finer-grained metric derived from phonological feature theory, feature error rate (FER). For the challenge, we prepared a new data resource of responses to two confrontation naming tests found in AphasiaBank, extracting audio and adding new phonemic transcripts for each response. Abstract We present the outcome of the Post-Stroke Speech Transcription (PSST) challenge.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |