Bone-conducted speech enhancement using deep denoising autoencoder

By Hung-Ping Liu, Yu Tsao, Chiou-Shann Fuh. 2018

63 citations recorded by the source corpus.

Abstract Bone-conduction microphones (BCMs) capture speech signals based on the vibrations of the speaker's skull and exhibit better noise-resistance capabilities than normal air-conduction microphones (ACMs) when transmitting speech signals. Because BCMs only capture the low-frequency portion of speech signals, their frequency response is quite different from that of ACMs. When replacing an ACM with a BCM, we may obtain satisfactory results with respect to noise suppression, but the speech quality and intelligibility may be degraded due to the nature of the solid vibration. The mismatched characteristics of BCM and ACM can also impact the automatic speech recognition (ASR) performance, and it is infeasible to recreate a new ASR system using the voice data from BCMs. In this study, we propose a novel deep-denoising autoencoder (DDAE) approach to bridge BCM and ACM in order to improve speech quality and intelligibility, and the current ASR could be employed directly without recreating a new system. Experimental results first demonstrated that the DDAE approach can effectively improve speech quality and intelligibility based on standardized evaluation metrics. Moreover, our proposed system can significantly improve the ASR performance by a notable 48.28% relative character error rate (CER) reduction (from 14.50% to 7.50%) under quiet conditions. In an actual noisy environment (sound pressure from 61.7 dBA to 73.9 dBA), our proposed system with a BCM outperforms an ACM, yielding an 84.46% reduction in the relative CER (proposed system: 9.13% and ACM: 58.75%).

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

SEANet: A Multi-modal Speech Enhancement Network (2020, methodology): “Similarly, multi-modal inputs are combined in [25] using deep denoising autoencoders that reconstruct Mel-scale features fed to an ASR system.”
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, methodology): “These have been used for very diverse applications like diabetes detection [118], action detection for surveillance [119], feature learning for process pattern recognition [120], denoising for speech enhancement [121] [122], fault diagnosis [123], social image understanding [124], low light image en”