Deep causal speech enhancement and recognition using efficient long-short term memory Recurrent Neural Network.

ABSTRACT: Long short-term memory (LSTM) has been effectively used to represent sequential data in recent years. However, LSTM still struggles with capturing the long-term temporal dependencies. In this paper, we propose an hourglass-shaped LSTM that is able to capture long-term temporal correlations by reducing the feature resolutions without data loss. We have used skip connections in non-adjacent layers to avoid gradient decay. In addition, an attention process is incorporated into skip connections to emphasize the essential spectral features and spectral regions. The proposed LSTM model is applied to speech enhancement and recognition applications. The proposed LSTM model uses no future information, resulting in a causal system suitable for real-time processing. The combined spectral feature sets

SUBMITTER: Li Z 

PROVIDER: S-EPMC10763955 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature