基于CNN的降噪,用于具有离散波纹转换 (DWT) 预处理的多通道语音增强系统
Pavani Cherukuru1,2, Mumtaz Begum Mustafa1
1Department of Software Engineering, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, Malaysia.
PeerJ. Computer science
|March 4, 2024
概括
一个新的DWT-CNN-MCSE系统显著改善了噪音环境中的语音增强,特别是在低信号对噪音比率 (SNR) 的情况下. 这种先进的多通道语音增强 (MCSE) 方法在具有挑战性的声学条件下优于现有系统.
科学领域:
- 信号处理 信号处理
- 人工智能的人工智能
- 声学 声学 在声学方面
背景情况:
- 多通道语音增强 (MCSE) 系统对于改善噪音环境中的语音质量至关重要.
- 现有的算法经常与低信号噪声比 (SNR) 条件和高频环境噪声作斗争.
- 有效的降噪对于在各种声学环境中运行的语音设备至关重要.
研究的目的:
- 评估一种新的多通道语音增强 (MCSE) 系统,用于静止和非静止环境中的降噪.
- 为了比较现有的MCSE系统 (BAV-MCSE) 与拟议的DWT-CNN-MCSE系统在不同SNR级别 (-10 dB至20 dB) 的性能.
- 评估离散波波变换 (DWT) 和卷积神经网络 (CNN) 在增强噪音语音信号方面的有效性.
主要方法:
- 实验使用了AURORA和LibriSpeech数据集,其中包括各种环境噪音.
- 现有的BAV-MCSE系统采用光束成型,适应性降噪和语音活动检测.
- 拟议的DWT-CNN-MCSE系统集成了离散波波变换 (DWT) 预处理与卷积神经网络 (CNN) 进行无声化.
主要成果:
- 在20dB SNR下,BAV-MCSE实现了93.77%的高词识别率 (WRR),但在-10dB SNR下平均只有5.64%.
- 拟议的DWT-CNN-MCSE系统在低SNR下表现出卓越的性能,在-10dBSNR下达到70.55%的WRR.
- 在DWT-CNN-MCSE系统显示了最显著的改善,在-10dB SNR时,WRR增加了64.91%.
结论:
- 在低SNR条件下,DWT-CNN-MCSE系统在语音增强方面提供了显著的改进,特别是在低SNR条件下.
- 这种新的方法有效地过环境噪音,在具有挑战性的声学场景中提高语音可理解性.
- 整合DWT和CNN为先进的多通道语音增强提供了强大的解决方案.
相关概念视频
Downsampling
157
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
157
Upsampling
236
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
236
Deconvolution
159
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
159
Reconstruction of Signal using Interpolation
195
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
195
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
1.1K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.1K
Sampling Continuous Time Signal
241
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
241


