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

Citations Over TimeTop 1% of 2015 papers

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.

Related Papers

• → Scaling speech enhancement in unseen environments with noise embeddings(2018)16 cited
• → Building Acoustic and Language Model for Continuous Speech Recognition in Bahasa Indonesia(2020)4 cited
• → Improving Low Resources Arabic Speech Recognition using Data Augmentation(2022)1 cited
• Data Selection in the Framework of Automatic Speech Recognition(2017)
• → Indigenuous Vocabulary Reformulation for Continuousyorùbá Speech Recognition In M-Commerce Using Acoustic Nudging-Based Gaussian Mixture Model(2021)