Improving Speaker Diarrization for Low-Resourced Sarawak Malay Language Conversational Speech Corpus

Mohd Zulhafiz, Rahim and Sarah Flora, Samson Juan and Fitri Suraya, Mohamad (2023) Improving Speaker Diarrization for Low-Resourced Sarawak Malay Language Conversational Speech Corpus. In: 2023 International Conference on Asian Language Processing (IALP), 18-20 November 2023, Singapore.

PDF Improving Speaker Diarization.pdf Download (653kB)

Abstract

Speaker diarization plays a vital role in speech transcription involving conversations as it improves the transcribed content’s accuracy, comprehension, and usability. By having a speech transcription diarized, the conversation data has a more structured presentation, allowing for a variety of applications that rely on accurate speaker attribution. Even so, speaker diarization is a field that has been less explored for low-resourced languages, as current resources that have been optimized and applied in speaker diarization are mostly for more developed and well-resourced languages, such as English, Spanish or French. In this paper, we propose an approach to using pseudo-labelled speech data to perform self-training on the x-vector models to improve diarization accuracy. The proposed method uses almost 13 hours Sarawak Malay unlabeled conversational speech corpus obtained from the Kalaka: Language Map of Malaysia website for training, as well as 1 hour and 26 minutes of manually labeled Sarawak Malay speech data for testing and evaluation. We demonstrate how speaker diarization models can be fine-tuned with the pseudo-labeled data.

Actions (For repository members only: login required)

View Item