Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation

no code implementations • 25 Dec 2019 • Lu Huang, Gaofeng Cheng, Pengyuan Zhang, Yi Yang, Shumin Xu, Jiasong Sun

The experimental results show that uPIT outperforms cPIT when LC-BLSTM is used during inference.

Speech Separation

An Improved Residual LSTM Architecture for Acoustic Modeling

no code implementations • 17 Aug 2017 • Lu Huang, Jiasong Sun, Ji Xu, Yi Yang

Long Short-Term Memory (LSTM) is the primary recurrent neural networks architecture for acoustic modeling in automatic speech recognition systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1