基于参数估计和感知提升的语音增强降噪算法

为了提高单通道语音增强降噪算法的整体质量,该文从噪声消除和语音感知两个角度出发对传统语音增强算法进行改进,通过引入多种处理手段来达到最佳优化效果。首先在参数估计方面,把基于弱语音出现的平滑算法加入到基于固定先验信噪比的软判决方法中来解决噪声谱过估计问题,并根据语音帧存在概率动态调整平滑因子,从而提高先验信噪比的跟踪效果。其次在语音质量感知提升方面,采用谐波恢复的方法重建语音段的高频谐波分量,并采用相位补偿和增益平滑的方法消除静默段和语音段的音乐噪声。实验结果表明,相比传统算法,该文算法通过引入参数估计改进模块和感知质量提升模块,在消噪效果和语音质量两方面均得到了较大的提高,并适用于多类噪声环境和信噪比条件。     

基于幅度压缩滤波的清浊音分类及基音估计

该文针对传统算法在实环境(不同噪声类型和信噪比)下容易发生清浊误判和基音估计错误问题,提出一种基于幅度压缩基音估计滤波(PEFAC)的清浊音分类及基音估计方法。首先,通过PEFAC削弱语音的低频噪声,提取出基音谐波;然后,采用基于对称平均幅度和函数的脉冲序列加权算法(SIM)确定谐波数目;最后,利用动态规划估计出基音,用基于3元素特征矢量的高斯混合模型对清浊音进行分类。仿真结果表明,在实环境下,所提方法能有效抑制清浊误判及基音估计错误现象的发生,性能优于传统方法。     

基于噪声估计的改进能量熵语音端点检测算法

针对传统能量熵的短时能量与子带谱熵容易受噪声环境影响,低信噪比下端点检测性能下降的问题,提出一种基于噪声估计的改进能量熵语音端点检测算法.首先对语音进行噪声估计并以此计算语音存在概率;然后利用估计的噪声能量修正短时能量,用语音存在概率作为加权系数优化子带谱熵,并将两者结合生成改进的能量熵;最后给出基于噪声估计的动态门限以及实时的端点检测策略.实验结果表明,在信噪比5 dB、0 dB的多种噪声环境中,基于噪声估计的改进能量熵端点检测算法相比传统能量熵算法与改进子带能谱比算法,检测正确率平均提升7％.     

An autocorrelation pitch detector and voicing decision withconfidence measures developed for noise-corrupted speech

The authors describe an integrated speech feature extraction method consisting of: (1) a pitch detector; (2) a voicing decision to correctly partition speech into voiced and unvoiced intervals; (3) a confidence measure which reflects the probabilistic accuracy of the voicing decision; (4) a confidence measure which reflects the expected deviation of the pitch estimate from the true pitch and the probabilistic accuracy of this deviation; and (5) smoothing techniques for the pitch detector, the voicing decision, and the two confidence measures. The focus of their research is on voiced and unvoiced speech corrupted by high levels of white noise. The voicing decision and the confidence measures are developed by observing the behavior of three features derived from the autocorrelation function and experimentally fitting curves to the data. This integrated set of algorithms is statistically analyzed for speech at seven signal-to-noise ratios     

基于听觉感知的LSA-MMSE改进型语音增强方法

传统增强方法的增益函数对每个频点都进行估计,必然会引进相对较多的语音失真.为了提高低信噪比下的语音增强效果,提出了一种计算掩蔽概率的方法,得到优化的语音增强方法.基于听觉感知特性,对噪声被掩蔽部分的带噪语音谱和未掩蔽部分采用不同处理方法.增强后的语音可以表示为这两个状态下单独估计的加权和,其中权重与噪声被掩蔽概率有关.通过与Virag的方法、LSA-MMSE估计等方法进行比较,实验结果表明所提的增强方法能在低信噪比下有效地抑制残留噪声的同时保持更小的语音失真.     

基于噪声谱约束的二值掩码估计语音增强算法

提出一种基于噪声谱约束的二值掩码估计语音增强算法,用以提高低信噪比情况下的语音可懂度。首先分析了低信噪比时,先验信噪比过估对噪声谱估计函数的影响;再分别对先验信噪比和噪声谱估计函数进行修正;最后,根据修正后的噪声谱估计函数和先验信噪比判断出噪声谱被欠估的时频单元,估计出二值掩码值,并对相应的增强后语音时频单元进行幅度谱约束。仿真结果表明,在几种常见背景噪声的低信噪比情况下,相比于传统维纳滤波法,本文算法效果更好,能有效的提高语音可懂度。      

结合差分阵列与幅度谱减的双麦语音增强算法

为了抑制小型语音通信设备中的方向性噪声干扰问题,提出了一种结合差分阵列与幅度谱减的双麦语音增强算法。该算法首先利用一阶差分阵列技术,对两麦克风采集到的带噪语音信号进行处理,得到语音通道信号和噪声通道信号。接着利用差分阵列处理后的两通道信号对语音通道信号的信噪比进行估计。最后利用幅度谱减法对语音通道信号中残留噪声进行消除。针对语音通道信号的信噪比估计,本文给出了两种新奇的计算方法。仿真实验表明,该算法有效的抑制了方向噪声,改善了语音的质量,去噪效果及语音质量均优于对比算法。      

Performance Evaluation of Silence-Feature Normalization Model using Cepstrum Features of Noise Signals

Speech enhancement algorithms play an important role in speech signal processing. Over the past several decades, many algorithms have been studied for speech enhancement. A speech enhancement algorithm uses a noise removal method and a statistical model filter to analyze the speech signal in the frequency domain. Spectral subtraction and Wiener filters have been used as representative algorithms. These algorithms have excellent speech enhancement performance, but suffer from deterioration in performance due to specific noise or low signal-to-noise ratio (SNR) environments. In addition, according to estimations of erroneous noise, a noise existing in a voice signal is maintained so that a spectrum corresponding to a voice signal is distorted, or a frame corresponding to a voice signal cannot be retrieved, and voice recognition performance deteriorates. The problem of deterioration in speech recognition performance arises from the difference between speech recognition and training model. We use silence-feature normalization model as a methodology to improve the recognition rate resulting from the difference in the noisy environments. Conventional silence-feature normalization has a problem in that the silent part of the energy increases, which affects recognition performance due to unclear boundaries categorizing the voice. In this study, we use the cepstrum feature of the noise signals in the silence-feature normalization model to improve the performance of silence-feature normalization in a signal with a low SNR by setting a reference value for voiced and unvoiced classification. As a result of recognition rate confirmation, the recognition rates improve in performance, compared with other methods.     

色噪声环境中TLS-ESPRIT谐波谱重构语音增强研究

为了提高语音在色噪声环境中的信噪比,提出了一种基于总体最小二乘旋转不变子空间技术（TLS—ESPRIT）谐波谱重构语音增强方法。通过对观察数据矩阵进行奇异值分解,有效地将信号及噪声分开。运用TLS—ESPRIT算法对语音谐波信号进行谱估计,重构语音信号,消除了帧与帧之间的噪声残留,得到了在巴克域上与原始语音几乎相同的语音信号。     

一种高精度改进型SHR基音检测算法

利用正弦语音模型中浊音存在的谐波与子谐波,在SHR(subharninctoharmonicratio)算法的基础上,提出了一种改进型高精度基音检测算法ISHR(improvingsubharninctoharmonicratio)。根据幅度调制和频率调制在语音分析中的特性、频域中幅度值和自相关频率比值,该方法采用基于正弦模型的均方误差对语音进行检测,提取出准确基音。仿真结果表明此种算法在基音提取中具有高精度及高可靠性。     

Voiced/Nonvoiced Detection Based on Robustness of Voiced Epochs

In this paper, a new method for voiced/nonvoiced detection based on epoch extraction is proposed. Zero-frequency filtered speech signal is used to extract the instants of significant excitation (or epochs). The robustness of the method to extract epochs in the voiced regions, even with small amount of additive white noise, is used to distinguish voiced epochs from random instants detected in nonvoiced regions. The main feature of the proposed method is that it uses the strength of glottal activity as against using the periodicity of the signal. Performance of the proposed algorithm is studied on TIMIT and CMU ARCTIC databases, for two different noise types, white and vehicle noise from the NOISEX database, at different signal-to-noise ratios (SNRs). The proposed method performs similar or better than the popular normalized crosscorrelation based voiced/nonvoiced detection used in the open source utility wavesurfer, especially at lower SNRs.      

一种基于支持向量机的含噪语音的清/浊/静音分类的新方法

本文将支持向量机(SVM)方法应用于语音信号的清/浊/静音检测中,提出并验证了一种在各种信噪比等级下将语音信号有效地分为清音、浊音和静音三类信号的新型分类算法.首先,在高信噪比情况下,本文采用了G.729B VAD中的四个差分参数作为SVM分类器的输入特征参数,进行了静音分类的对比实验,得到了优于G.729B VAD和BP神经网络传统算法的实验结果,说明引入这种机器学习方法做语音分类是可行的,并分析讨论了在核函数不同的情况下支持向量机在实验中所表现出的性能.其次,又讨论了在低信噪比条件下,如何通过对含噪语音建立统计模型,提取对噪音免疫的统计特征参数,并给出了一种对时变背景噪声自适应的估计方法.最后,通过在不同噪音环境下的对比实验结果,验证了本文所提出的算法在中低信噪比情况下的分类性能要优于其他传统算法.     

基于时域Gammatone滤波特征的广播语种识别

针对广播语种识别问题,提出一种语音时域滤波方法,用gammatone时域函数与预处理后的语音信号进行卷积滤波,再分帧加窗并求对数化能量得到时域GF(gammatone filterbank)特征.将特征参数图像化表示,然后通过VGG19和Resnet34分类网络进行语种识别实验.同时,也使用自动色阶算法对加噪语音的图像...     

Estimating the pitch period of voiced speech

In speech processing an estimation of the speech pitch period is important. Real time pitch detection is only possible by the selection of an efficient algorithm suitable for implementation on a programmable processor or in special-purpose hardware. The use of the periodogram algorithm (p.a.) is proposed to detect the pitch period of voiced speech. This algorithm is attractive for the following reasons: (a) it has no multiply operation; (b) when implemented on a 16-bit computer (e.g. microprocessor) the computation can be done in integer arithmetic without exceeding the microprocessor's dynamic range; (c) it is a simple technique for estimating the pitch period with reasonable accuracy. Results of the analysis of speech signals and sinusoids using the periodogram algorithm are presented and comparisons are made with the average magnitude difference function (a.m.d.f.) which is an alternative method of estimating the pitch period of the voiced speech.     

低信噪比下多参数融合的自适应语音端点检测

传统语音端点检测方法利用语音和噪声在某单一参数特征上的差异进行信号中语音起止点的切分,但不同参数在低信噪比不同噪声环境下表现不稳定,鲁棒性差。因此,本文提出了基于均匀子带谱方差,能熵比,梅尔倒谱距离,似然比四种参数相融合的语音端点检测方法。该方法能自适应地改变各参数阈值,并通过实时监测噪声段能熵比的值确定所采用的投票判决机制,从而进行语音端点判定。实验结果表明,该方法在低信噪比下较常用的端点检测方法有更高的检测正确率及鲁棒性,对语音信号后续处理工作有一定的借鉴意义。      

Efficient a priori SNR estimation based on parameter adaptive spectral method

The a priori signal-to-noise (SNR) is one of the most important parameters in the short-time spectrum estimation techniques in speech enhancement. A new and convenient algorithm to estimate the priori SNR is involved in this paper. In this paper, the priori and posterior SNR of intra-frame are defined which can trace the variation of the a priori SNR of each frame better and can solve the problem of delay involved by the traditional approaches. Simulation shows that, the performance of the proposed algorithm is better than the traditional estimators in terms of log-spectral distance and the improvement segmental SNR, especially in the no stationary noise environments.     

语音清浊音差分LSF参数矢量量化方法

差分LSF参数的动态范围小于LSF参数,可作为一种新的模型参数应用于语音编码中。分析了2种新的差分LSF参数矢量量化方法：增强差分分裂参数矢量量化（EnhancedDifferentialSplitVectorQuantization,EDSVQ）和增强EDSVQ（EnhancedEDSVQ,EEDSVQ）,并采用英语清、浊音的差分LSF参数进行分裂矢量量化实验。结果表明,EEDSVQ能有效抑制直接对差分LSF参数进行矢量量化引起的量化误差传递和叠加;在分配相同量化比特数的情况下．清音的量化效果优于浊音．为获得相同量化效果可减少对清音的量化比特数。     

非平稳环境下基于人耳听觉掩蔽特性的语音增强

传统的语音增强算法往往仅对平稳噪声或缓慢变化的噪声有效,且残留的音乐噪声较大。对此,本文研究了一种非平稳环境下基于听觉掩蔽效应的语音增强算法。该算法对传统谱减法的功率谱估计算法进行改进,根据最小均方误差原则和语音信号的听觉掩蔽阈值调整功率谱估计的参数,并引入了基于最小值统计特性的噪声估计算法,使估计的噪声更好地跟踪噪声的变化。实验结果表明:该算法对平稳和非平稳的噪声都得到较好的增强效果,且较好地抑制了音乐噪声。     

基于改进语音存在概率的自适应噪声跟踪算法

在非平稳环境下,由于时间递归平均噪声功率谱估计算法会出现跟踪延迟和估计误差等问题,本文采用一种新的方式对其核心部分语音存在概率（speech presence probability, spp）进行估计。利用时域特征能量与频域特征谱熵的比值能熵比作为新的特征来构建其与spp的正比关系,从而得到当前语音帧的spp估计值;然后用双平滑系数对该值进行平滑;最后结合时间递归平均算法得到估计的噪声功率谱。该算法充分利用语音帧频点的特征信息控制spp的估计值,以此自适应地跟踪噪声变化。实验结果表明:在地空通信环境下,该方法能够准确且连续地跟踪噪声功率谱、快速响应其变化。集成到语音增强系统后,可以提高语音质量,降低残留噪声。      

一种稳健的语音信号检测方法

本文提出一和种基于谱相关技术的语音信号检测方法。该方法以信号幅度谱的自相关函数为基础,通过峰值检测来达到自动检测语音的目的。