تقرير
Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition
| العنوان: | Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition |
|---|---|
| المؤلفون: | Chan, David M., Ghosh, Shalini, Tulsiani, Hitesh, Rastrow, Ariya, Hoffmeister, Björn |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Sound |
| الوصف: | While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recognition results. Existing assistant systems collect large numbers of these unsuccessful interactions, but these systems usually fail to learn from these interactions, even in an offline fashion. In this work, we introduce CLC: Contrastive Learning for Conversations, a family of methods for contrastive fine-tuning of models in a self-supervised fashion, making use of easily detectable artifacts in unsuccessful conversations with assistants. We demonstrate that our CLC family of approaches can improve the performance of ASR models on OD3, a new public large-scale semi-synthetic meta-dataset of audio task-oriented dialogues, by up to 19.2%. These gains transfer to real-world systems as well, where we show that CLC can help to improve performance by up to 6.7% over baselines. We make OD3 publicly available at https://github.com/amazon-science/amazon-od3 . Comment: To appear in ICASSP 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2401.02417 |
| رقم الأكسشن: | edsarx.2401.02417 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |