提高耳语音可懂度的非对称压缩语音增强方法

提出两种基于非对称代价函数的耳语音增强算法,将语音增强过程中的放大失真和压缩失真区分对待。Modified ItakuraSaito (MIS)算法对放大失真给予更多的惩罚,而Kullback-Leibler (KL)算法则对压缩失真给予更多的惩罚。实验结果表明,在低于—6 dB的低信噪比情况中,经MIS算法增强后的耳语音的可懂度相比传统算法有显著提高;而KL算法则获得了同最小均方误差语音增强算法近似的可懂度提高效果,证实了耳语音中的放大失真和压缩失真对于耳语音可懂度的影响并不相同,低信噪比时较大的压缩失真有助于提高耳语音可懂度,而高信噪比时的压缩失真对耳语音可懂度影响较小。      

一种自适应变阶谱减降噪算法在电子耳蜗中的应用

由于传统谱减语音增强存在残留的"音乐噪声",因此基于传统谱减法降噪的电子耳蜗(CI)感知的声音品质也会受到影响.为提高CI的抗噪性,本文提出了一种自适应变阶谱减算法,并将该方法应用于电子耳蜗的语音增强中.根据CI电极对应的频带关系,该算法先对采集的带噪声音信号功率谱进行Bark子带划分,并在每个Bark子带中根据信噪比的变化进行谱减阶数和系数的自适应调节,使各子带噪声更均衡地去除,基本消除了传统方法存在的"音乐噪声".基于该算法的电子耳蜗ACE仿真实验及测听结果表明,与传统谱减法相比,改进的算法能更好地抑制背景噪声和残留噪声,仿真得到的CI合成音感知更好和更清晰.     

一种增强带噪语音可懂度的新算法

一般的语音增强算法在强噪声环境中只能提高信噪比,不能提高可懂度。本文提出用可调节白噪声代替信号中非语音部分的语音可懂度增强处理新算法。实验证明此方法能明显改善强噪声时的语音可懂度,能对低至-10dB的带噪语音信号进行有效的可懂度增强。     

联合深度神经网络和凸优化的单通道语音增强算法

噪声估计的准确性直接影响语音增强算法的好坏,为提升当前语音增强算法的噪声抑制效果,有效求解无约束优化问题,提出一种联合深度神经网络(DNN)和凸优化的时频掩蔽优化算法进行单通道语音增强。首先,提取带噪语音的能量谱作为DNN的输入特征;接着,将噪声与带噪语音的频带内互相关系数(ICC Factor)作为DNN的训练目标;然后,利用DNN模型得到的互相关系数构造凸优化的目标函数;最后,联合DNN和凸优化,利用新混合共轭梯度法迭代处理初始掩蔽,通过新的掩蔽合成增强语音。仿真实验表明,在不同背景噪声的低信噪比下,相比改进前,新的掩蔽使增强语音获得了更好的对数谱距离(LSD)、主观语音质量(PESQ)、短时客观可懂度(STOI)和分段信噪比(segSNR)指标,提升了语音的整体质量并且可以有效抑制噪声。      

噪声对单耳语言可懂度的影响

单耳通信时,周边噪声对语言可懂度产生影响。针对信号侧语音信号强度70dB时,研究3种不同类型噪声下,干扰侧不同强度噪声和信号侧不同信噪比情况的语言可懂度。实验结果表明:当信号侧信噪比大于某一阈值时,干扰侧噪声对可懂度不产生显著影响,该阈值同噪声类型有关;而在信号侧低信噪比的情形下,干扰侧适当强度噪声可提高信号侧语言可懂度,最佳干扰噪声级为78—82dB,过大的干扰侧噪声级导致可懂度下降。基于心理声学和生理学的初步机理发现:噪声环境下的语音识别中,对侧耳中耳肌肉伸缩对噪声感知的抑制提高了信号侧语言可懂度。      

用于无监督语音降噪的听觉感知鲁棒主成分分析法

针对现有稀疏低秩分解语音降噪方法对人耳听觉感知特性应用不充分、语音失真易被感知的问题,提出了一种用于语音降噪的听觉感知鲁棒主成分分析法。由于耳蜗基底膜对于频率感知具有非线性特性,该方法采用耳蜗谱图作为语噪分离的基础。此外,选用符合人耳听觉感知特性的板仓-斋田距离度量作为优化目标函数,在稀疏低秩建模过程中引入非负约束以使分解分量更符合实际物理含义,并在交替方向乘子法框架下推导了具有闭合解形式的迭代优化算法。文中方法在语音降噪时是完全无监督的,无需预先训练语音或噪声模型。多种类型噪声和不同信噪比条件下的仿真实验验证了该方法的有效性,噪声抑制效果较目前同类算法更为显著,且降噪后语音的可懂度和总体质量有所提高、至少相当。      

改进的正交匹配追踪的语音增强算法*

为了提高传统正交匹配追踪（Orthogonal Matching Pursuit,OMP ）算法的语音增强性能和运算速度,本研究基于稀疏编码理论,提出了一种改进的OMP算法的语音增强算法。其一,将K-奇异值分解（K-singular value decomposition,K-SVD）算法与OMP算法相结合,通过设置能量阈值的方法,提高OMP算法的语音增强性能;其二,通过改进传统OMP算法中信号稀疏逼近的计算方法,提高算法的运算速度。改进的OMP算法的语音增强算法与传统K-SVD语音增强算法相比,采用PESQ评价增强语音的质量,NCM评价语音的可懂度。在NCM的值基本保持不变的情况下,PESQ的值平均提高约12.47%,取得了更好的增强效果。取得了更好的增强效果。改进的OMP算法的运算速度与传统OMP算法相比提高近一倍。     

卷积噪声环境下语音信号鲁棒特征提取

提出了一种基于独立分量分析(ICA)的语音信号鲁棒特征提取算法,用以解决在卷积噪声环境下语音信号的训练与识别特征不匹配的问题。该算法通过短时傅里叶变换将带噪语音信号从时域转换到频域后,采用复值ICA方法从带噪语音的短时谱中分离出语音信号的短时谱,然后根据所得到的语音信号短时谱计算美尔倒谱系数(MFCC)及其一阶差分作为特征参数。在仿真与真实环境下汉语数字语音识别实验中,所提算法相比较传统的MFCC其识别正确率分别提升了34.8%和32.6%。实验结果表明基于ICA方法的语音特征在卷积噪声环境下具有良好的鲁棒性。      

单通道语音增强算法对汉语语音可懂度影响的研究

考察了当前常用的几种单通道语音增强算法对汉语语音可懂度的影响。受不同类型噪音干扰的语音经过5种单通道语音增强算法的处理后,播放给具有正常听力水平的被试进行听辩,考察增强后语音的可懂度。实验结果表明,语音增强算法并不能改进语音的可懂度水平;通过分析具体的错误原因,发现听辩错误主要来自于音素错误,与声调关系不大;而且,同英文的辨识结果相比,一些增强算法对于中、英文可懂度影响差异显著。      

采用联合字典优化的噪声鲁棒性语音转换算法

针对含噪语音难以实现有效的语音转换,本文提出了一种采用联合字典优化的噪声鲁棒性语音转换算法。在联合字典的构成中,语音字典采用后向剔除算法(Backward Elimination algorithm,BE)进行优化,同时引入噪声字典,使得含噪语音与联合字典相匹配。实验结果表明,在保证转换效果的前提下,后向剔除算法能够减少字典帧数,降低计算量。在低信噪比和多种噪声环境下,本文算法与传统NMF算法和基于谱减法消噪的NMF转换算法相比具有更好的转换效果,噪声字典的引入提升了语音转换系统的噪声鲁棒性。      

A simulation study of harmonics regeneration in noise reduction for electric and acoustic stimulation

Recent research results show that combined electric and acoustic stimulation (EAS) significantly improves speech recognition in noise, and it is generally established that access to the improved F0 representation of target speech, along with the glimpse cues, provide the EAS benefits. Under noisy listening conditions, noise signals degrade these important cues by introducing undesired temporal-frequency components and corrupting harmonics structure. In this study, the potential of combining noise reduction and harmonics regeneration techniques was investigated to further improve speech intelligibility in noise by providing improved beneficial cues for EAS. Three hypotheses were tested: (1) noise reduction methods can improve speech intelligibility in noise for EAS; (2) harmonics regeneration after noise reduction can further improve speech intelligibility in noise for EAS; and (3) harmonics sideband constraints in frequency domain (or equivalently, amplitude modulation in temporal domain), even deterministic ones, can provide additional benefits. Test results demonstrate that combining noise reduction and harmonics regeneration can significantly improve speech recognition in noise for EAS, and it is also beneficial to preserve the harmonics sidebands under adverse listening conditions. This finding warrants further work into the development of algorithms that regenerate harmonics and the related sidebands for EAS processing under noisy conditions.     

Temporal envelope compensation for robust phoneme recognition using modulation spectrum

A robust feature extraction technique for phoneme recognition is proposed which is based on deriving modulation frequency components from the speech signal. The modulation frequency components are computed from syllable-length segments of sub-band temporal envelopes estimated using frequency domain linear prediction. Although the baseline features provide good performance in clean conditions, the performance degrades significantly in noisy conditions. In this paper, a technique for noise compensation is proposed where an estimate of the noise envelope is subtracted from the noisy speech envelope. The noise compensation technique suppresses the effect of additive noise in speech. The robustness of the proposed features is further enhanced by the gain normalization technique. The normalized temporal envelopes are compressed with static (logarithmic) and dynamic (adaptive loops) compression and are converted into modulation frequency features. These features are used in an automatic phoneme recognition task. Experiments are performed in mismatched train/test conditions where the test data are corrupted with various environmental distortions like telephone channel noise, additive noise, and room reverberation. Experiments are also performed on large amounts of real conversational telephone speech. In these experiments, the proposed features show substantial improvements in phoneme recognition rates compared to other speech analysis techniques. Furthermore, the contribution of various processing stages for robust speech signal representation is analyzed.     

Contribution of frequency modulation to speech recognition in noise

Cochlear implants allow most patients with profound deafness to successfully communicate under optimal listening conditions. However, the amplitude modulation (AM) information provided by most implants is not sufficient for speech recognition in realistic settings where noise is typically present. This study added slowly varying frequency modulation (FM) to the existing algorithm of an implant simulation and used competing sentences to evaluate FM contributions to speech recognition in noise. Potential FM advantage was evaluated as a function of the number of spectral bands, FM depth, FM rate, and FM band distribution. Barring floor and ceiling effects, significant improvement was observed for all bands from 1 to 32 with the additional FM cue both in quiet and noise. Performance also improved with greater FM depth and rate, which might reflect resolved sidebands under the FM condition. Having FM present in low-frequency bands was more beneficial than in high-frequency bands, and only half of the bands required the presence of FM, regardless of position, to achieve performance similar to when all bands had the FM cue. These results provide insight into the relative contributions of AM and FM to speech communication and the potential advantage of incorporating FM for cochlear implant signal processing.     

Effects of directional microphone and adaptive multichannel noise reduction algorithm on cochlear implant performance

Although cochlear implant (CI) users have enjoyed good speech recognition in quiet, they still have difficulties understanding speech in noise. We conducted three experiments to determine whether a directional microphone and an adaptive multichannel noise reduction algorithm could enhance CI performance in noise and whether Speech Transmission Index (STI) can be used to predict CI performance in various acoustic and signal processing conditions. In Experiment I, CI users listened to speech in noise processed by 4 hearing aid settings: omni-directional microphone, omni-directional microphone plus noise reduction, directional microphone, and directional microphone plus noise reduction. The directional microphone significantly improved speech recognition in noise. Both directional microphone and noise reduction algorithm improved overall preference. In Experiment II, normal hearing individuals listened to the recorded speech produced by 4- or 8-channel CI simulations. The 8-channel simulation yielded similar speech recognition results as in Experiment I, whereas the 4-channel simulation produced no significant difference among the 4 settings. In Experiment III, we examined the relationship between STIs and speech recognition. The results suggested that STI could predict actual and simulated CI speech intelligibility with acoustic degradation and the directional microphone, but not the noise reduction algorithm. Implications for intelligibility enhancement are discussed.     

Spectral and temporal cues for phoneme recognition in noise

Cochlear implant users receive limited spectral and temporal information. Their speech recognition deteriorates dramatically in noise. The aim of the present study was to determine the relative contributions of spectral and temporal cues to speech recognition in noise. Spectral information was manipulated by varying the number of channels from 2 to 32 in a noise-excited vocoder. Temporal information was manipulated by varying the low-pass cutoff frequency of the envelope extractor from 1 to 512 Hz. Ten normal-hearing, native speakers of English participated in tests of phoneme recognition using vocoder processed consonants and vowels under three conditions (quiet, and +6 and 0 dB signal-to-noise ratios). The number of channels required for vowel-recognition performance to plateau increased from 12 in quiet to 16-24 in the two noise conditions. However, for consonant recognition, no further improvement in performance was evident when the number of channels was > or =12 in any of the three conditions. The contribution of temporal cues for phoneme recognition showed a similar pattern in both quiet and noise conditions. Similar to the quiet conditions, there was a trade-off between temporal and spectral cues for phoneme recognition in noise.     

Spectrotemporal analysis and cochlear hearing impairment: effects of frequency selectivity, temporal resolution, signal frequency, and rate of modulation

The detection of 500- or 2000-Hz pure-tone signals in unmodulated and modulated noise was investigated in normal-hearing and sensorineural hearing-impaired listeners, as a function of noise bandwidth. Square-wave modulation rates of 15 and 40 Hz were used in the modulated noise conditions. A notched noise measure of frequency selectivity and a gap detection measure of temporal resolution were also obtained on each subject. The modulated noise results indicated a masking release that increased as a function of increasing noise bandwidth, and as a function of decreasing modulation rate for both groups of listeners. However, the improvement of threshold with increasing modulated noise bandwidth was often greatly reduced among the sensorineural hearing-impaired listeners. It was hypothesized that the masking release in modulated noise may be due to several types of processes including across-critical band analysis (CMR), within-critical band analysis, and suppression. Within-band effects appeared to be especially large at the higher frequency region and lower modulation rate. In agreement with previous research, there was a significant correlation between frequency selectivity and masking release in modulated noise. At the 500-Hz region, masking release was correlated more highly with the filter skirt and tail measures than with the filter passband measure. At the 2000-Hz region, masking release was correlated more with the filter passband and skirt measures than with the filter tail measure. The correlation between gap detection and masking release was significant at the 40-Hz modulation rate, but not at the 15-Hz modulation rate. The results of this study suggest that masking release in modulated noise is limited by frequency selectivity at low modulation rates, and by both frequency selectivity and temporal resolution at high modulation rates. However, even when the present measures of frequency selectivity and temporal resolution are both taken into account, significant variance in masking release still remains unaccounted for.     

Companding to improve cochlear-implant speech recognition in speech-shaped noise

Nonlinear sensory and neural processing mechanisms have been exploited to enhance spectral contrast for improvement of speech understanding in noise. The "companding" algorithm employs both two-tone suppression and adaptive gain mechanisms to achieve spectral enhancement. This study implemented a 50-channel companding strategy and evaluated its efficiency as a front-end noise suppression technique in cochlear implants. The key parameters were identified and evaluated to optimize the companding performance. Both normal-hearing (NH) listeners and cochlear-implant (CI) users performed phoneme and sentence recognition tests in quiet and in steady-state speech-shaped noise. Data from the NH listeners showed that for noise conditions, the implemented strategy improved vowel perception but not consonant and sentence perception. However, the CI users showed significant improvements in both phoneme and sentence perception in noise. Maximum average improvement for vowel recognition was 21.3 percentage points (p<0.05) at 0 dB signal-to-noise ratio (SNR), followed by 17.7 percentage points (p<0.05) at 5 dB SNR for sentence recognition and 12.1 percentage points (p<0.05) at 5 dB SNR for consonant recognition. While the observed results could be attributed to the enhanced spectral contrast, it is likely that the corresponding temporal changes caused by companding also played a significant role and should be addressed by future studies.     

时域递归滤波对微光成像视距影响的研究

 针对微光成像中噪声较大及视距较短的问题,提出了一种自适应时域递归滤波算法。该算法通过自动调节时域递归的滤波系数来提高信噪比和延伸视距。实验显示当滤波系数分别为0.50、0.75和0.875时,视距分别能延伸至原始的1.73倍、2.64倍和3.87倍,所得到的视距延伸与理论值基本保持一致。实验结果表明该算法在保持图像运动部分清晰的同时,还能有效地消除噪声并延伸微光成像系统的视距。     

基于BLCD分解与ACO-DBN网络的光纤振动信号识别

针对光纤振动信号受噪声干扰严重、特征提取单一和识别时间长的问题,提出了改进的局部特征尺度分解和蚁群算法优化深度置信网络的识别方法。首先,采用三次B样条函数插值拟合均值曲线改进局部特征尺度分解算法,并对原始信号进行分解得到一系列内禀尺度分量之和。其次,利用峭度因子和能谱系数构成融合指标筛选有效分量。然后,分别提取有效分量在时域、频域和时-频域的熵值特征进行融合并降维。最后,将综合特征向量馈入蚁群优化后的深度置信网络进行训练和识别,提高算法效率和识别率。采用实测数据进行实验验证,结果表明,信噪比平均提升8 dB,信号平均识别率可达95.83%,平均识别时间为0.715 s。     

Combined spectral and temporal enhancement to improve cochlear-implant speech perception

The present study examined the effect of combined spectral and temporal enhancement on speech recognition by cochlear-implant (CI) users in quiet and in noise. The spectral enhancement was achieved by expanding the short-term Fourier amplitudes in the input signal. Additionally, a variation of the Transient Emphasis Spectral Maxima (TESM) strategy was applied to enhance the short-duration consonant cues that are otherwise suppressed when processed with spectral expansion. Nine CI users were tested on phoneme recognition tasks and ten CI users were tested on sentence recognition tasks both in quiet and in steady, speech-spectrum-shaped noise. Vowel and consonant recognition in noise were significantly improved with spectral expansion combined with TESM. Sentence recognition improved with both spectral expansion and spectral expansion combined with TESM. The amount of improvement varied with individual CI users. Overall the present results suggest that customized processing is needed to optimize performance according to not only individual users but also listening conditions.