Phoneme Segmentation Using Self-Supervised Speech Models
This work addresses phoneme segmentation for speech processing, with incremental improvements in method and evaluation clarity.
The paper tackles phoneme segmentation by applying transfer learning from self-supervised speech models, achieving state-of-the-art performance on TIMIT and Buckeye datasets in both supervised and unsupervised settings.
We apply transfer learning to the task of phoneme segmentation and demonstrate the utility of representations learned in self-supervised pre-training for the task. Our model extends transformer-style encoders with strategically placed convolutions that manipulate features learned in pre-training. Using the TIMIT and Buckeye corpora we train and test the model in the supervised and unsupervised settings. The latter case is accomplished by furnishing a noisy label-set with the predictions of a separate model, it having been trained in an unsupervised fashion. Results indicate our model eclipses previous state-of-the-art performance in both settings and on both datasets. Finally, following observations during published code review and attempts to reproduce past segmentation results, we find a need to disambiguate the definition and implementation of widely-used evaluation metrics. We resolve this ambiguity by delineating two distinct evaluation schemes and describing their nuances.