Permutation invariant training of deep models for speaker-independent multi-talker speech separation - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Dong Yu, Morten Kolbæk, Zheng-Hua Tan, Jesper Jensen 0001. Permutation invariant training of deep models for speaker-independent multi-talker speech separation. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, LA, USA, March 5-9, 2017. pages 241-245, IEEE, 2017. [doi]

The following publications are possibly variants of this publication:

Single-channel multi-talker speech recognition with permutation invariant trainingYanmin Qian, Xuankai Chang, Dong Yu 0001. speech, 104:1-11, 2018. [doi]

Recognizing Multi-Talker Speech with Permutation Invariant TrainingDong Yu, Xuankai Chang, Yanmin Qian. interspeech 2017: 2456-2460 [doi]

Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant trainingMorten Kolbaek, Dong Yu, Zheng-Hua Tan, Jesper Jensen 0001. mlsp 2017: 1-6 [doi]

runs on WebDSL