تقرير
Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations
العنوان: | Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations |
---|---|
المؤلفون: | Dhawan, Kunal, Koluguri, Nithin Rao, Jukić, Ante, Langman, Ryan, Balam, Jagadeesh, Ginsburg, Boris |
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 |
الوصف: | Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noise robustness. Drawing upon our findings, we introduce a codec ASR pipeline that outperforms Encodec at similar bit-rate. Remarkably, it also surpasses the state-of-the-art results achieved by strong self-supervised models on the 143 languages ML-SUPERB benchmark despite being smaller in size and pretrained on significantly less data. Comment: Accepted at Interspeech 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.03495 |
رقم الأكسشن: | edsarx.2407.03495 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |