Bibliographic citations
Cabrera, D., (2024). Construcción de recursos para la detección y clasificación automática de disfluencias producidas por tartamudez en español [Pontificia Universidad Católica del Perú]. http://hdl.handle.net/20.500.12404/28908
Cabrera, D., Construcción de recursos para la detección y clasificación automática de disfluencias producidas por tartamudez en español []. PE: Pontificia Universidad Católica del Perú; 2024. http://hdl.handle.net/20.500.12404/28908
@mastersthesis{renati/1661580,
title = "Construcción de recursos para la detección y clasificación automática de disfluencias producidas por tartamudez en español",
author = "Cabrera Díaz, Daniel Alonso",
publisher = "Pontificia Universidad Católica del Perú",
year = "2024"
}
This thesis focused on the development of computational resources for the detection and classification of stuttering disfluencies in Spanish, spanning from the collection and annotation of audio data to the implementation of a machine learning model and data augmentation strategies. Audios in Spanish from five participants with stuttering were collected, adhering to the SEP-28K dataset standards and supported by two specialists in stuttering. Although the controlled nature of the recordings limited the diversity of observed disfluencies, these audios provided a solid foundation for the model development. The model was based on the DisfluencyNet and pre-trained using wav2vec 2.0 XLSR53, leveraging its robust multilingual database. The model demonstrated its ability to identify and classify disfluencies in Spanish, though its performance was inferior compared to similar models in English, highlighting the need for more data. To enhance disfluency detection, two data augmentation strategies were implemented. The first involved pitch variations, reverberation addition, and white noise, effectively doubling the available data. Although this strategy improved recall for certain disfluencies, precision and F1 results were mixed. The second strategy, using voice cloning with the XTTS-v2 model, generated new audios that emulated natural disfluencies, such as prolongations and blocks. While it enhanced recall, particularly in later rounds of data augmentation, precision and F1 continued to be challenging. Future research will focus on expanding the annotation of disfluencies in spontaneous speech contexts and processing the remaining audios from the initial corpus to explore improvements in classification and detection of disfluencies. Additionally, advanced voice cloning methods and other audio modification techniques will be explored to enrich the datasets and enhance the detection and classification models.
This item is licensed under a Creative Commons License