تقرير
Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network
| العنوان: | Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network |
|---|---|
| المؤلفون: | Pylkkönen, Janne, Ukkonen, Antti, Kilpikoski, Juho, Tamminen, Samu, Heikinheimo, Hannes |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | Adaption of end-to-end speech recognition systems to new tasks is known to be challenging. A number of solutions have been proposed which apply external language models with various fusion methods, possibly with a combination of two-pass decoding. Also TTS systems have been used to generate adaptation data for the end-to-end models. In this paper we show that RNN-transducer models can be effectively adapted to new domains using only small amounts of textual data. By taking advantage of model's inherent structure, where the prediction network is interpreted as a language model, we can apply fast adaptation to the model. Adapting the model avoids the need for complicated decoding time fusions and external language models. Using appropriate regularization, the prediction network can be adapted to new domains while still retaining good generalization capabilities. We show with multiple ASR evaluation tasks how this method can provide relative gains of 10-45% in target task WER. We also share insights how RNN-transducer prediction network performs as a language model. Comment: 5 pages, 2 figures. Accepted to Interspeech 2021 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2104.11127 |
| رقم الأكسشن: | edsarx.2104.11127 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |