噪声情况下采用稀疏非负矩阵分解与深度吸引子网络的人声分离算法

为实现噪声情况下的人声分离,提出了一种采用稀疏非负矩阵分解与深度吸引子网络的单通道人声分离算法。首先,通过训练得到人声与噪声的字典矩阵,将其作为先验信息从带噪混合语音中分离出人声与噪声的系数矩阵;然后,根据人声系数矩阵中不同的声源成分在嵌入空间中的相似性不同,使用深度吸引子网络将其分离为各声源语音的系数矩阵;最后,使用分离得到的各语音系数矩阵与人声的字典矩阵重构干净的分离语音。在不同噪声情况下的实验结果表明,本文算法能够在抑制背景噪声的同时提高分离语音的整体质量,优于结合声噪人声分离模型的对比算法。      

结合幅度谱和功率谱字典的语音增强方法

从双路字典学习、噪声功率谱估计、语音幅度谱重构角度提出了一种改进的谱特征稀疏表示语音增强方法。在字典学习阶段,融合功率谱与幅度谱特征,采用区分性字典降低语音字典和噪声字典的相干性;在语音增强阶段,提出一种噪声功率谱估计方法对非平稳噪声进行跟踪估计;考虑到幅度谱和功率谱特征对不同噪声的适应程度不同,设计了语音重构权值表。对分别由幅度谱和功率谱恢复而来的两路信号进行自适应加权重构,结合相位补偿函数得到增强后的语音信号。实验结果表明,该方法在平稳、非平稳噪声环境下相比于单一谱特征的语音增强方法平均提高31.6%,改善了语音增强方法的性能。      

Speech enhancement based on the discrete Gabor transform and multi-notch adaptive digital filters

This paper presents a new method to speech enhancement based on time-frequency analysis and adaptive digital filtering. The proposed method for dual-channel speech enhancement was developed by tracking frequencies of corrupting signal by the discrete Gabor transform (DGT) and implementing multi-notch adaptive digital filter (MNADF) at those frequencies. Since no a priori knowledge of the noise source statistics is required this method differs from traditional speech enhancement methods. Specifically, the proposed method was applied to the case where speech quality and intelligibility deteriorate in the presence of background noise. Speech coders and automatic speech recognition (ASR) systems are designed to act on clean speech signals. Therefore, corrupted speech signals by the noise must be enhanced before their processing. The method uses a primary input containing the corrupted speech signal while a reference input containing the noise only. In this paper, we designed MNADF instead of single-notch adaptive digital filter and used DGT to track frequencies of corrupting signal because fast filtering process and fast measure of the time-dependent noise frequency are of great importance in speech enhancement process. Therefore, MNADF was implemented to take advantage of fast filtering process. Different types of noises from Noisex-92 database were used to degrade real speech signals. Objective measures, the study of the speech spectrograms and global signal-to-noise ratio (SNR), segmental SNR (segSNR), Itakura-Saito distance measure as well as subjective listing test demonstrated consistently superior enhancement performance of the proposed method over traditional speech enhancement method such as spectral subtraction. Combining MNADF and DGT, excellent speech enhancement was obtained.     

A speech enhancement method based on Kalman filtering

I.IntroductionKa1manfilteringisjustamethodtoestimatestatistica1lythestateoftheobservedsystemfromthecorruptedsigna1s,andthiskindofcstimationisarecurrcneeestimationbasedon1inear,nonbiasandminimumvariance.Moreover,Ka1manfilteringisapplicabletonon-sta-honarysignalsandtime-variantdynamicsystem.Therefore,Kalmanfilteringisveryapplica-bletoenhancingthespeechsigna1sthatarecorruptedbynoise.ThispaperreportStheconcretcmethodofenhanccmentofnoisyspccchanditscxperimentresults.Experimentsindicate:Afterthes…     

Speech enhancement using linearly constrained adaptive constant directivity beam-formers

This paper aims to extend previous work on constant directivity beam-formers (CDBs), for the case of multiple desired speech sources, by designing a linearly constrained adaptive CDB (LCA-CDB) which preserves the beam-pattern in multiple look directions. Also, the proposed LCA-CDB, adaptively, minimizes the transient noise power in the output of the beam-former, and furthermore, produces some controlled nulls (controlled in both amplitude and angle) on the beam-pattern. This strengthens the system in removing permanent directional noises and producing a frequency-invariant beam-pattern with multiple main-lobes and controlled nulls in arbitrary frequency bands. Through simulating the system and the acoustical situations, the authors have tried to demonstrate the capability of the proposed method in enhancement of broadband and telephony speech in the presence of various noise sources (transient noise, permanent noise and uncorrelated white Gaussian noise). The simulation results obtained in this study confirm the efficiency of the proposed method in suppression of environmental noises.     

采用L1/2稀疏约束的梅尔倒谱系数语音重建方法

提出了一种利用L_1/2稀疏约束从梅尔倒谱系数重建语音时域信号方法。从梅尔倒谱系数估计语音幅度谱是一个欠定问题,现有的方法均采用幅度谱最小均方误差估计或采用L1正则化进行幅度谱的稀疏约束。相比于L₁正则化模型,L_1/2的稀疏约束特性更强,为此,本文在从梅尔倒谱系数估计语音幅度谱时引入L_1/2正则化约束,并利用求解的稀疏幅度谱估计相位谱,最后利用估计的频谱重建时域语音信号。实验结果表明,与幅度谱最小均方误差法相比,本文算法所估计出的语音信号具有更高的语音质量;在噪声环境下进行语音重建实验,与L₁正则化幅度谱估计方法相比,本文算法重建的语音质量更好,表现出更好抗噪性。      

Model-based speech enhancement using a bone-conducted signal

Codebook-based single-microphone noise suppressors, which exploit prior knowledge about speech and noise statistics, provide better performance in nonstationary noise. However, as the enhancement involves a joint optimization over speech and noise codebooks, this results in high computational complexity. A codebook-based method is proposed that uses a reference signal observed by a bone-conduction microphone, and a mapping between air- and bone-conduction codebook entries generated during an offline training phase. A smaller subset of air-conducted speech codebook entries that accurately models the clean speech signal is selected using this reference signal. Experiments support the expected improvement in performance at low computational complexity.     

Evaluation of speech transmission in open public spaces affected by combined noises

In the present study, the effects of interference from combined noises on speech transmission were investigated in a simulated open public space. Sound fields for dominant noises were predicted using a typical urban square model surrounded by buildings. Then road traffic noise and two types of construction noises, corresponding to stationary and impulsive noises, were selected as background noises. Listening tests were performed on a group of adults, and the quality of speech transmission was evaluated using listening difficulty as well as intelligibility scores. During the listening tests, two factors that affect speech transmission performance were considered: (1) temporal characteristics of construction noise (stationary or impulsive) and (2) the levels of the construction and road traffic noises. The results indicated that word intelligibility scores and listening difficulty ratings were affected by the temporal characteristics of construction noise due to fluctuations in the background noise level. It was also observed that listening difficulty is unable to describe the speech transmission in noisy open public spaces showing larger variation than did word intelligibility scores.     

扩散噪声下协方差矩阵重构的语音分离与降噪

针对传统多通道语音分离算法在扩散噪声下性能下降的问题,提出了一种用于语音分离及降噪的空间协方差模型及参数估计方法。该方法将扩散噪声视为独立声源,利用由导向矢量重构的空间协方差矩阵建模目标声源的空间特性,并通过空间协方差分析方法估计用于语音分离的多通道维纳滤波器。同时,还提出了一种联合该方法的后置滤波器参数框架,为输出信号降噪和失真的折中提供了更多选择。在扩散噪声下的单目标和多目标实验中,所提方法的语音提取和分离性能都优于对比算法,联合参数的后置滤波器可提供更为符合人们要求的降噪语音,验证了所提模型与参数估计方法的有效性。      

Noise source identification of diesel engine based on variational mode decomposition and robust independent component analysis

Through separating and identifying the noise sources of diesel engine, each independent noise obtained can be used as reference for the noise reduction, condition monitoring and fault diagnosis. In the noise source identification of diesel engine, the combustion noise and the piston slap noise are found to be overlapped in time domain and frequency domain. So it is intricate to accurately separate them. Therefore, the noise source identification method which is based on variational mode decomposition (VMD), robust independent component analysis (RobustICA) and continuous wavelet transform (CWT) is proposed. In the test, a 6-cylinder diesel engine was tested in a semi-anechoic chamber. The lead wrapped method was adopted to wrap No. 1–5 cylinders so as to isolate the interference noises, only the No. 6 cylinder part was bared. The single channel noise signal of cylinder head was measured. Then the variational mode decomposition algorithm is utilized to decompose the noise signal into several variational mode components. The RobustICA algorithm is adopted to extract the independent components. Finally, the continuous wavelet transform and the prior knowledge of diesel engine are applied to further identify the separated results. The results show that by using the proposed method to separate and identify the radiation noise of the cylinder head of the diesel engine, the independent components obtained are respectively the combustion noise and the piston slap noise. Comparing with the EEMD-RobustICA-CWT method, each independent noises obtained through the proposed method are more accurate and pure with less other interference noises.