A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation

Autor:	Higuchi, Yosuke, Chen, Nanxin, Fujita, Yuya, Inaguma, Hirofumi, Komatsu, Tatsuya, Lee, Jaesong, Nozaki, Jumon, Wang, Tianzi, Watanabe, Shinji
Rok vydání:	2021
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Computation and Language Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time applications, an increasing number of NAR models have been explored in different fields to mitigate the performance gap against AR models. In this work, we conduct a comparative study of various NAR modeling methods for end-to-end automatic speech recognition (ASR). Experiments are performed in the state-of-the-art setting using ESPnet. The results on various tasks provide interesting findings for developing an understanding of NAR ASR, such as the accuracy-speed trade-off and robustness against long-form utterances. We also show that the techniques can be combined for further improvement and applied to NAR end-to-end speech translation. All the implementations are publicly available to encourage further research in NAR speech processing. Comment: Accepted to ASRU2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2110.05249 Zobrazit plný text záznamu View this record from Arxiv