The Performance of Wearable Speech Enhancement System Under Noisy Environment: An Experimental Study

Cherukuru, Pavani; Mustafa, Mumtaz Begum; Subramaniam, Hema

doi:10.1109/access.2021.3137878

Cited by 3 publications

(4 citation statements)

References 39 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental design of this research was based on the researchers’ previous work Cherukuru, Mumtaz Begum & Hema (2021) , which was for environmental noises at different levels of SNRs to determine the limitations of the existing algorithms in handling environmental noises. From our previous work ( Cherukuru, Mumtaz Begum & Hema, 2021 ), we found that the existing MCSE shows an acceptable recognition rate at high SNR levels but not for low SNR levels. To overcome the problem of low recognition rate for low SNR levels, this research proposed a deep learning-based algorithms to improve the recognition accuracy of the MCSE system.…”

Section: Methodsmentioning

confidence: 99%

“…• Device configuration is based on the researchers’ previous work Cherukuru, Mumtaz Begum & Hema (2021) …”

Section: Methodsmentioning

confidence: 99%

“…According to Cherukuru, Mumtaz Begum & Hema (2021) only white Gaussian stationary noise was tested with beamforming, ANR and VAD algorithms in MCSE between 0 dB to 60 dB SNRs, and proving that MCSE is particularly effective at 20 dB SNR ( Palla et al, 2017 ). For the stationary white Gaussian noise, the word recognition rate decreased for low noises at 15 dB to −10 dB, respectively ( Cherukuru, Mumtaz Begum & Hema, 2021 ). The negative dB had a lower WRR than the positive dB but low for 15 dB to −10 dB non-stationary noise.…”

Section: Research Backgroundmentioning

confidence: 99%

“…The deep learning algorithm is one of the state-of-the-art algorithms in the speech enhancement domain ( Rownicka, Bell & Renals, 2020 ; Ochiai, Delcroix & Nakatani, 2020 ), which has been proven to have acceptable performance in handling different levels of noise in speech enhancement based on the computing platform. Among the deep learning algorithms, the very deep convolution neural network (VDCNN-conv) reported the highest WRR at 90.45% and an average WRR of 87.45% for environmental noises ( Cherukuru, Mumtaz Begum & Hema, 2021 ). However, MCSE systems have never been experimented with deep learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

CNN-based noise reduction for multi-channel speech enhancement system with discrete wavelet transform (DWT) preprocessing

Cherukuru,

Mustafa

2024

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Speech enhancement algorithms are applied in multiple levels of enhancement to improve the quality of speech signals under noisy environments known as multi-channel speech enhancement (MCSE) systems. Numerous existing algorithms are used to filter noise in speech enhancement systems, which are typically employed as a pre-processor to reduce noise and improve speech quality. They may, however, be limited in performing well under low signal-to-noise ratio (SNR) situations. The speech devices are exposed to all kinds of environmental noises which may go up to a high-level frequency of noises. The objective of this research is to conduct a noise reduction experiment for a multi-channel speech enhancement (MCSE) system in stationary and non-stationary environmental noisy situations with varying speech signal SNR levels. The experiments examined the performance of the existing and the proposed MCSE systems for environmental noises in filtering low to high SNRs environmental noises (−10 dB to 20 dB). The experiments were conducted using the AURORA and LibriSpeech datasets, which consist of different types of environmental noises. The existing MCSE (BAV-MCSE) makes use of beamforming, adaptive noise reduction and voice activity detection algorithms (BAV) to filter the noises from speech signals. The proposed MCSE (DWT-CNN-MCSE) system was developed based on discrete wavelet transform (DWT) preprocessing and convolution neural network (CNN) for denoising the input noisy speech signals to improve the performance accuracy. The performance of the existing BAV-MCSE and the proposed DWT-CNN-MCSE were measured using spectrogram analysis and word recognition rate (WRR). It was identified that the existing BAV-MCSE reported the highest WRR at 93.77% for a high SNR (at 20 dB) and 5.64% on average for a low SNR (at −10 dB) for different noises. The proposed DWT-CNN-MCSE system has proven to perform well at a low SNR with WRR of 70.55% and the highest improvement (64.91% WRR) at −10 dB SNR.

show abstract

Section: Methodsmentioning

confidence: 99%

“…• Device configuration is based on the researchers’ previous work Cherukuru, Mumtaz Begum & Hema (2021) …”

Section: Methodsmentioning

confidence: 99%

Section: Research Backgroundmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CNN-based noise reduction for multi-channel speech enhancement system with discrete wavelet transform (DWT) preprocessing

Cherukuru,

Mustafa

2024

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Speech Enhancement and Recognition Using Deep Learning Algorithms: A Review

Hepsiba¹,

Vinotha²,

Anand³

2023

Computational Vision and Bio-Inspired Computing

View full text Add to dashboard Cite

A rotating machinery fault feature extraction approach based on an adaptive wavelet denoising method and synthetic detection index

Zhou¹,

Zhang²,

Lu³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Feature extraction from vibration signals plays a vital role in rotating machinery fault diagnosis. The noise contained in the signals will interfere with the fault feature extraction result. Wavelet denoising is a commonly used method to reduce the noise, but its parameters are generally selected based on subjective experience. With this problem in mind, an adaptive wavelet denoising method is proposed in this paper. Using permutation entropy to evaluate the signal noise level and taking its minimum value as the fitness function, the intelligent optimization algorithm is applied to optimize the wavelet denoising parameters. Based on this adaptive wavelet denoising method and a synthetic detection index, a new feature extraction approach is proposed. Results from simulation experiments and engineering applications prove that the signal denoising performance of the adaptive wavelet denoising method and the results of the fault feature extraction approach are satisfactory.

show abstract

The Performance of Wearable Speech Enhancement System Under Noisy Environment: An Experimental Study

Cited by 3 publications

References 39 publications

CNN-based noise reduction for multi-channel speech enhancement system with discrete wavelet transform (DWT) preprocessing

CNN-based noise reduction for multi-channel speech enhancement system with discrete wavelet transform (DWT) preprocessing

Speech Enhancement and Recognition Using Deep Learning Algorithms: A Review

A rotating machinery fault feature extraction approach based on an adaptive wavelet denoising method and synthetic detection index

Contact Info

Product

Resources

About