噪声环境下说话人识别性能的研究

为了提高噪声环境下说话人识别系统的识别性能,将基于听觉掩蔽效应的语音增强技术作为预处理器,对语音信号首先进行降噪处理,提高输入信号的信噪比。实验证明,经过降噪处理的语音信号送入说话人识别系统,提高了系统的识别性能。     

噪声环境下说话人识别的组合特征提取方法

针对在干净语音环境下识别率很高的说话人识别系统,在噪声环境下识别率显著降低的缺点,本文结合具有多分辨率分析特点的小波变换技术,提出一种基于小波变换的组合特征提取算法,以提高说话人识别系统在噪声环境下的识别性能。对40个说话人的语音库SUDA2002-D2,在噪声环境下进行的识别实验结果表明,本文提出的组合特征提取算法可以在噪声环境下有效地提高说话人识别系统的识别性能。     

听觉特性和语谱特性在说话人识别中的应用

大多数说话人识别系统当由实验室走向实际应用时,环境噪声的存在会造成其识别性能下降。为了提高噪声环境下说话人识别系统的识别性能,将基于听觉特性和语谱特性的语音增强技术作为预处理器,首先对语音信号进行降噪处理,提高输入信号的信噪比。实验证明,经过降噪处理的语音信号送入说话人识别系统,提高了系统的识别性能。     

基于小波变换的鲁棒型特征提取及说话人识别

说话人识别系统在实际应用中面临的主要困难之一是鲁棒性问题,干净语音环境下识别率很高的说话人识别系统,在有噪语音环境下识别性能显著降低。解决这一问题的方法之一是寻找具有鲁棒性的特征参数。本文结合具有多分辨率分析特点的小波变换技术,提出一种基于小波变换的鲁棒型特征提取算法,以提高说话人识别系统在噪声环境下的识别性能。对40个说话人的语音库SUDA2002-D2,在加性高斯白噪声环境下进行的识别实验结果表明,本文提出的特征提取算法可以有效地提高说话人识别系统在噪声环境下的识别性能。     

噪声环境中基于VQ说话人识别

噪声环境下,为了提高说话人识别系统的鲁棒性,需要对系统进行各种抗噪声处理。采用梅尔频率倒谱系数作为语音的特征参数,矢量量化方法进行模式匹配,将改进的基于听觉掩蔽效应的语音增强器作为预处理器,对语音信号首先进行降噪处理。语音增强器实验结果表明,经过降噪处理后提高了输入信号的信噪比,减少了语音失真,同时很好地抑制了背景噪声和残余音乐噪声。将经过降噪处理的语音信号送入说话人识别系统,提高了系统的识别性能。     

双通道能量差后滤波语音增强算法统计分析和改进

双通道能量差后滤波语音增强算法在语音通信系统的噪声抑制技术中有较好的应用前景,然而其理论性能和局限性还未得到充分研究。为此,本文采用统计分析方法研究了双通道能量差后滤波语音增强算法的性能,分析了相干性、平滑因子及噪声估计误差对算法的影响。理论和仿真结果表明,噪声估计误差和平滑因子严重影响该算法的降噪性能。依据此分析结果,本文提出一种基于非平稳噪声估计和功率谱自适应平滑的双通道能量差后滤波算法。测试结果表明,本文提出的算法在不增加语音失真的前提下,能更有效地抑制非平稳噪声,段信噪比提高(SegSNRI)和语音质量感知评估(PESQ)等客观评价指标都表明本文的算法优于其它几种经典的后滤波算法。      

加性噪声条件下鲁棒说话人确认

基于非负矩阵分解的语音去噪,在提高语音信号信噪比的同时,也会引起语音失真,从而导致噪声环境下说话人确认系统性能下降.本文提出基于分区约束非负矩阵分解的语音去噪方法（Nonnegative Matrix Factorization with Partial Constrains,PCNMF）,目的是在未知和非平稳噪声条件下提高话人确认系统的鲁棒性.PCNMF在满足分区约束条件的基础上分别构建语音字典和噪声字典.考虑到传统语音训练产生的语音字典往往含有一定的噪声成分,PCNMF通过数学模型产生基音及泛音频谱,在此基础上利用该频谱模仿人声的共振峰结构来合成字典,从而保证语音字典纯净性.另一方面,为了克服传统噪声字典构建方法带来的部分噪声信息丢失问题,PCNMF对在线分离出的噪声样本进行分帧和短时傅里叶变换,然后以帧为单位线性组合生成噪声字典.性能评估实验引入了多种噪声类型,实验结果表明PCNMF可有效提高说话人确认系统的鲁棒性,特别是在未知和非平稳噪声条件下其等错率相比基线系统（Multi-Condition）平均降低了5.2%.     

一种强混响环境下的盲语音分离算法

强混响环境下语音信号的频域盲分离问题是盲源分离领域的一个难点,主要是因为混合系统的脉冲响应时间过长,甚至超过信号的非平稳时间,导致算法性能下降。本文针对这个问题提出了一种解决方法,在用一个短时傅立叶变换将时域卷积混合信号转化为频域的过程,再在时频域上使用另一个短时傅立叶变换,将信号变换到调制谱域,这样较长的脉冲响应就被转化为调制谱域上的瞬时混合形式,而瞬时混合情形则采用独立向量分析(IVA)算法来避免排序模糊性问题。计算机仿真实验证实了该算法在强混响环境下优于传统频域盲分离算法。      

小波去噪在缓变机械故障检测中的应用

针对缓变机械故障信号频率低易受高频噪声干扰的情况,提出了利用小波变换对振动信号进行降噪的方法,通过与传统的经典滤波方法相比,小波变换降噪方法在去除掉高频噪声的同时也保留了信号的高频成分,是一种比傅立叶变换更有效的降噪方法。通过实验数据的比较分析,验证了小波去噪是针对机械信号的环境特点最为有效的降噪方法,从而达到有效提取有用信号并探测目标的目的。     

一种基于自适应滤波的语音降噪方法研究

分析和研究自适应滤波和小波变换法的原理及方法,提出了一种新的综合使用自适应滤波和小波变换法的语音降噪方法。该方法首先用仿生小波变换法对带噪声的语音信号进行小波分解,将小渡变换法分离出来的噪声信号作为自适应滤波器的输入。最后选择用最小均方误差（LMS）的自适应算法对带噪声语音信号进行降噪处理,实现了信噪分离,去除语音信号中的噪声信号。实验结果表明,该方法对语音信号有较为明显的降噪效果。     

Integrating recursive minimum tracking and codebook-based noise estimation for improved reduction of non-stationary noise

Conventional single-channel noise reduction algorithms typically have problems with non-stationary noise. Popular algorithms such as minimum statistics or voice-activity-detector-based methods rely on the assumption that the noise spectral characteristics change very slowly over time. Codebook-based approaches try to overcome this problem by incorporating a priori knowledge about speech and different noise types. These approaches perform a joint estimation of the speech and noise spectra on a frame-by-frame basis. The frames are typically 20-40 ms long so that fast fluctuations of the signal characteristics can be tracked instantaneously. However, these methods require a pitch estimator to prevent speech distortion as well as residual noise in voiced speech frames. In addition, they are not very robust against model mismatch. In this paper, we propose an integrated noise estimation algorithm that combines the ability of codebook-based algorithms to track non-stationary noise with the robustness of a recursive minimum-tracking-based noise estimation algorithm. An objective and subjective evaluation is provided. Results confirm the superiority of the proposed algorithm in non-stationary noise scenarios compared to state-of-the-art algorithms.     

Improved Speech Denoising Algorithm Based on Discrete Fractional Fourier Transform

The speech signal and noise signal are the typical non-stationary signals,however the speech signa is short-stationary synchronously.Presently,the denoising methods are always executed in frequency domain due to the short-time stationarity of the speech signal.In this article,an improved speech denoising algorithm based on discrete fractional Fourier transform（DFRFT）is pre sented.This algorithm contains linear optimal filtering and median filtering.The simulation shows that it can easily eliminate the noise compared to Wiener filtering improve the signal to noise ratio（SNR）,and enhance the original speech signal.     

A Wavelet Based Hybrid Threshold Transform Method for Speech Intelligibility and Quality in Noisy Speech Patterns of English Language

The paper proposes a method to improve the performance of speech communication system in a highly noisy industrial environment. For the improvement, different speech signals are considered which includes signals from different environments such as car noise, railway station, babble noise, street noise which are corrupted with additional noise as input data set for processing. This database is processed using suitable filters which will remove the effect of noise to some extent. Different algorithms have been proposed to minimize the effect of noise to a certain limit. The denoising algorithms are generally the different wavelet thresholding method which removes the noise from the speech signal. Many researchers have worked on soft and hard thresholding for image processing. The proposed method of hybrid thresholding comprises of both soft and hard thresholding process which is comparatively better method than the previous methods. The method can be implemented for the non-stationary noise and it also removes the problems of edges. Unlike the traditional way of using single value, different values are used for the adaptive filtering to remove the edges. During the course of experiments, the dataset of IIIT-H with a set of noisy files from Noizeus and AURORA database having sampling rate of 16 kHz has been used. Results are calculated with subjective and objective measures for fine and broad level quality assessment. SNR, SSNR, PSNR, NRMSE, and PESQ parameters are used as performance parameters and outperform with other combinations as compared to conventional methods. The hybrid threshold method yields better results with significant improvement in speech quality and intelligibility.

     

Objective estimation of the quality of radical noise suppression algorithms

There are compared six noise suppression algorithms with application of objective factors of the speech signal quality, and also with application of through quality factor of the system of automated speech recognition in form of speech recognition accuracy. It is shown that radical noise suppression algorithms are worse than traditional noise suppression algorithms by both restored speech quality and speech recognition accuracy due to essential signal distortion.     

基于加权噪声的递归平滑噪声功率谱估计

提出了一种噪声功率谱估计算法,该算法对加权后的带噪语音进行递归平滑,可以持续更新噪声并可应用于非平稳噪声环境中。为了避免在强语音后的弱语音区域出现噪声过估计,本文提出了用于计算加权函数的投影平滑算法。本文噪声估计算法可以快速跟踪噪声的变化并且没有过估计。实验结果表明,本文噪声估计算法应用于一个语音增强系统时,取得了较小的噪声分段估计误差及较好的感知语音质量评价(PESQ)得分。     

混沌背景下语音信号提取算法的研究

有效语音信号的提取在说话人识别中起着重要的作用,是声纹识别的主要研究内容之一。由于语音信号的非平稳性和不可预知因素的影响,决定用基于非线性时间序列的状态空间投影算法提取强噪声下的语音信号。该算法对其他场合微弱信号的检测也行之有效。     

语音业务中鲁棒性VAD算法合析

采用话音激活检测（Voiced Activity Detection，VAD）术的目的是检测语音通信时是否有话音存在，检测到静音时加以抑制，使其不占用或极少占用信道带宽，检测到话音时才对其进行压缩编码与传输。鲁棒性语音识别系统、数字移动通信和因特网实时语音传输等领域要求在恶劣声学环境条件下进行VAD检测，以节省带宽并抑制噪声，因此VAD技术是目前语音处理领域的重要问题。文中给出的几种最新VAD算法（EZCR—VAD，STAT-VAD和E-VAD）是在低信噪比环境下的话音检测具有很好的鲁棒性的算法。     

Speech Enhancement Algorithm Based on MMSE Short Time Spectral Amplitude in Whispered Speech

An improved method based on minimum mean square error-short time spectral amplitude （MMSE-STSA） is proposed to cancel background noise in whispered speech. Using the acoustic character of whispered speech, the algorithm can track the change of non-stationary background noise effectively. Compared with original MMSE-STSA algorithm and method in selectable mode Vo-coder （SMV）, the improved algorithm can further suppress the residual noise for low signal-to-noise radio （SNR） and avoid the excessive suppression. Simulations show that under the non-stationary noisy environment, the proposed algorithm can not only get a better performance in enhancement, but also reduce the speech distortion.     

一种基于噪声快速跟踪的语音增强算法

对解决传统减谱算法残留音乐噪声的问题,现有许多方法都无法达到理想效果。提出一种能在非平稳噪声环境下快速追踪噪声的语音增强方法,采用端点检测优化信噪比,达到较好的语音增强效果。实验表明,相比其他类似方法,在提高实时性、增加信噪比和抑制背景噪声和音乐噪声方面都有更好效果。     

并行子带HMM最大后验概率自适应非线性类估计算法

目前,自动语音识别(ASR)系统在实验室环境下获得了较高的识别率,但是在实际环境中,由于受到背景噪声和传输信道的影响,系统的识别性能急剧恶化.本文以听觉试验为基础,提出一种新的独立子带并行最大后验概率的非线性类估计算法,用以提高识别系统的鲁棒性.本算法利用多种噪声和识别内容功率谱差异,以及噪声在不同频带上对HMM影响的不同,采用多层感知机(MLP)对噪声环境下最大后验概率进行非线性映射,以减少识别系统由于环境不匹配而导致的识别性能下降.实验表明:该算法性能明显优于最大后验线性回归算法和Sangita提出的子带语音识别算法.