Papers by Khyathi Gayathri Mothika
Looks can be Deceptive: Distinguishing Repetition Disfluency from Reduplication (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research indicates that disfluencies can constitute up to 5.9% of words in spontaneous speech, with repetitions accounting for over half of these disfluency. |
| Approach: | They propose to use a dataset to analyze reduplication and repetition in speech using computational linguistics to evaluate transformer-based models. |
| Outcome: | The proposed models achieve macro F1 scores of up to 85.62% in Hindi, 83.95% in Telugu, and 84.82% in Marathi for reduplication-repetition classification. |