تقرير
On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition
العنوان: | On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition |
---|---|
المؤلفون: | Rossenbach, Nick, Schlüter, Ralf, Sakti, Sakriani |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
الوصف: | The rapid development of neural text-to-speech (TTS) systems enabled its usage in other areas of natural language processing such as automatic speech recognition (ASR) or spoken language translation (SLT). Due to the large number of different TTS architectures and their extensions, selecting which TTS systems to use for synthetic data creation is not an easy task. We use the comparison of five different TTS decoder architectures in the scope of synthetic data generation to show the impact on CTC-based speech recognition training. We compare the recognition results to computable metrics like NISQA MOS and intelligibility, finding that there are no clear relations to the ASR performance. We also observe that for data generation auto-regressive decoding performs better than non-autoregressive decoding, and propose an approach to quantify TTS generalization capabilities. Comment: Accepted at the SynData4GenAI 2024 workshop |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2407.21476 |
رقم الأكسشن: | edsarx.2407.21476 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |