Deep learning

Image (mathematics)

Literature

Artificial intelligence

Noise reduction

Voice activity detection

Speech enhancement

Mobile phone

Microphone

Microphone array

Dual (grammatical number)

Speech recognition

Computer network

Computer science

Low latency (capital markets)

Speech processing

Sound pressure

Telecommunications

Latency (audio)

Noise (video)

IEEE/ACM Transactions on Audio Speech and Language Processing

In mobile speech communication, speech signals can be severely corrupted by background noise when the far-end talker is in a noisy acoustic environment. To suppress background noise, speech enhancement systems are typically integrated into mobile phones, in which one or more microphones are deployed. In this study, we propose a novel deep learning based approach to real-time speech enhancement for dual-microphone mobile phones. The proposed approach employs a new densely-connected convolutional recurrent network to perform dual-channel complex spectral mapping. We utilize a structured pruning technique to compress the model without significantly degrading the enhancement performance, which yields a low-latency and memory-efficient enhancement system for real-time processing. Experimental results suggest that the proposed approach consistently outperforms an earlier approach to dual-channel speech enhancement for mobile phone communication, as well as a deep learning based beamformer.

Deep Learning Based Real-Time Speech Enhancement for Dual-Microphone Mobile Phones