تقرير
SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data
| العنوان: | SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data |
|---|---|
| المؤلفون: | Wang, Hsuan-Fu, Shih, Yi-Jen, Chang, Heng-Jui, Berry, Layne, Peng, Puyuan, Lee, Hung-yi, Wang, Hsin-Min, Harwath, David |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | The recently proposed visually grounded speech model SpeechCLIP is an innovative framework that bridges speech and text through images via CLIP without relying on text transcription. On this basis, this paper introduces two extensions to SpeechCLIP. First, we apply the Continuous Integrate-and-Fire (CIF) module to replace a fixed number of CLS tokens in the cascaded architecture. Second, we propose a new hybrid architecture that merges the cascaded and parallel architectures of SpeechCLIP into a multi-task learning framework. Our experimental evaluation is performed on the Flickr8k and SpokenCOCO datasets. The results show that in the speech keyword extraction task, the CIF-based cascaded SpeechCLIP model outperforms the previous cascaded SpeechCLIP model using a fixed number of CLS tokens. Furthermore, through our hybrid architecture, cascaded task learning boosts the performance of the parallel branch in image-speech retrieval tasks. Comment: Accepted to ICASSP 2024, Self-supervision in Audio, Speech, and Beyond (SASB) workshop |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.06959 |
| رقم الأكسشن: | edsarx.2402.06959 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |