In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose method for topic ID on spoken segments in low-resource languages, using a cascade of universal acoustic modeling, translation lexicons to English, and English-language topic classification. Next, instead of classifying each segment independently, we demonstrate that exploring the contextual dependencies across sequential segments can provide large improvements. In particular, we propose an attention-based contextual model which is able to leverage the contexts in a selective manner. We test both our contextual and non-contextual models on four LORELEI languages, and on all but one our attention-based contextual model significantly outperforms the context-independent models.
@article{arxiv.1807.06204,
title = {Low-Resource Contextual Topic Identification on Speech},
author = {Chunxi Liu and Matthew Wiesner and Shinji Watanabe and Craig Harman and Jan Trmal and Najim Dehak and Sanjeev Khudanpur},
journal= {arXiv preprint arXiv:1807.06204},
year = {2018}
}
Comments
Accepted for publication at 2018 IEEE Workshop on Spoken Language Technology (SLT)