title   
  

Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks

Chen, Zhuo and Watanabe, Shinji and Erdoğan, Hakan and Hershey, John R. (2015) Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks. In: InterSpeech 2015, Dresden, Germany

Full text not available from this repository.

Abstract

Long Short-Term Memory (LSTM) recurrent neural network has proven effective in modeling speech and has achieved outstanding performance in both speech enhancement (SE) and automatic speech recognition (ASR). To further improve the performance of noise-robust speech recognition, a combination of speech enhancement and recognition was shown to be promising in earlier work. This paper aims to explore options for consistent integration of SE and ASR using LSTM networks. Since SE and ASR have different objective criteria, it is not clear what kind of integration would finally lead to the best word error rate for noise-robust ASR tasks. In this work, several integration architectures are proposed and tested, including: (1) a pipeline architecture of LSTM-based SE and ASR with sequence training, (2) an alternating estimation architecture, and (3) a multi-task hybrid LSTM network architecture. The proposed models were evaluated on the 2nd CHiME speech separation and recognition challenge task, and show significant improvements relative to prior results.

Item Type:Papers in Conference Proceedings
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:28866
Deposited By:Hakan Erdoğan
Deposited On:24 Dec 2015 15:49
Last Modified:24 Dec 2015 15:49

Repository Staff Only: item control page