https://scholars.lib.ntu.edu.tw/handle/123456789/558963
Title: | What does a network layer hear? analyzing hidden representations of end-to-end asr through speech synthesis | Authors: | Li, C.-Y. Yuan, P.-C. HUNG-YI LEE |
Keywords: | Analysis; Automatic speech recognition; End-toend; Interpretability | Issue Date: | 2020 | Journal Volume: | 2020-May | Start page/Pages: | 6434-6438 | Source: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Abstract: | End-to-end speech recognition systems have achieved competitive results compared to traditional systems. However, the complex transformations involved between layers given highly variable acoustic signals are hard to analyze. In this paper, we present our ASR probing model, which synthesizes speech from hidden representations of end-to-end ASR to examine the information maintained after each layer calculation. Listening to the synthesized speech, we observe gradual removal of speaker variability and noise as the layer goes deeper, which aligns with the previous studies on how deep network functions in speech recognition. This paper is the first study analyzing the end-to-end speech recognition model by demonstrating what each layer hears. Speaker verification and speech enhancement measurements on synthesized speech are also conducted to confirm our observation further. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved. |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85091313173&partnerID=40&md5=533f36d93c07c028a7e28a04ad71f224 https://scholars.lib.ntu.edu.tw/handle/123456789/558963 |
DOI: | 10.1109/ICASSP40776.2020.9054675 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.