Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model
Abstrak
Recent advances in self-supervised speech models have shown significant improvement in many downstream tasks. However, these models predominantly centered on frame-level training objectives, which can fall short in spoken language understanding tasks that require semantic comprehension. Existing works often rely on additional speech-text data as intermediate targets, which is costly in the real-world setting. To address this challenge, we propose Pseudo-Word HuBERT (PW-HuBERT), a framework that integrates pseudo word-level targets into the training process, where the targets are derived from a visually-ground speech model, notably eliminating the need for speech-text paired data. Our experimental results on four spoken language understanding (SLU) benchmarks suggest the superiority of our model in capturing semantic information.
Penulis (8)
Hung-Chieh Fang
Nai-Xuan Ye
Yi-Jen Shih
Puyuan Peng
Hsuan-Fu Wang
Layne Berry
Hung-yi Lee
David Harwath
Akses Cepat
- Tahun Terbit
- 2024
- Bahasa
- en
- Sumber Database
- arXiv
- Akses
- Open Access ✓