Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training

Publication date: Available online 7 September 2018Source: Speech CommunicationAuthor(s): Yanmin Qian, Xuankai Chang, Dong YuAbstractAlthough great progress has been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures to address this problem under the assumption that only a single channel of mixed signal is available. Our technique extends permutation invariant training (PIT) by introducing the front-end feature separation module with the minimum mean square error (MSE) criterion and the back-end recognition module with the minimum cross entropy (CE) criterion. More specifically, during training we compute the average MSE or CE over the whol...

MedWorm Message: Have you tried our new medical search engine? More powerful than before. Log on with your social media account. 100% free.

from #Head and Neck by Sfakianakis via simeraentaxei on Inoreader https://ift.tt/2wUiwQL