基于改进阈值的小波域语音增强算法

提出了一种基于改进阈值的小波域语音增强算法.在阈值函数中引入参数,通过调整参数以获得较优的小波系数的阈值估计,使得改进阈值介于硬阈值与软阈值之间.利用改进阈值对染噪语音的小波系数进行阈值处理,达到了语音增强的目的.实验结果表明,该方法在抑制白噪声的同时减少了语音信息的损失,较硬阈值与软阈值的小波域语音增强方法相比,增强语音的信噪比、均方误差等性能均有明显的提高.     

Effects induced on the transverse-spatial-impulse response of an inhomogeneous photoreceptor with a nonsymmetric refractive index profile and arbitrarily located origin

Summary In a few earlier communications, spatial-transverse-impulse response (STIR) associated with the initial field transversely distributed across the entrance pupil of an inhomogeneous optical wave guide (photoreceptor) has been investigated. In the present work, effects of indetermination in the location of the origin on an arbitrarily defined refractive index profile, representing the degree of inhomogeity at the aperture pupil of a single receptor, have been studied. Some consequences related to a few possible technical applications have been discussed. To speed up publication, the authors of this paper have agreed to not receive the proofs for correction.     

用谱矩分析法实现语音的识别

本文应用语音信号的傅里叶谱的谱矩距离判决准则选择特征谱实现了语音的自动识别.实验表明,用这种方法实现的语音识别系统对三字一组的汉语数字语音串,识别精度约为99.8%。拒识率约为1%。     

Sustained oscillatory noise in the light responses of a retinal neuron

Summary In the retina of the turtle, prolonged illumination of the receptive field surrond can lead to the appearance of sustained oscillatory responses in horizontal cells. In most cells the oscillations consist of a main component of 40–50 Hz frequency modulated by slower waves. The experimental evidence suggests that these responses are due to the activation of the feeback circuit linking cone photoreceptors and horizontal cells in the vertebrate retina. Paper presented at the International Workshop ?Fluctuations in Physics and Biology: Stochastic Resonance, Signal Processing and Related Phenomena?, Elba, 5–10 June 1994.     

Acoustic characteristics of reticent speech

Reticent speakers differ from nonreticent speakers in vocal characteristics, such as fundamental frequency, frequency range, fluency, and intensity, which prompt negative impressions on the part of listeners. Waveform and spectrographic analyses were performed on the vocal cues of 19 reticent and nonreticent subjects (57 speech samples). Statistically significant differences were found in fluency between reticent and nonreticent speech. Reticent male speakers also showed significantly higher F₀, whereas reticent female speakers demonstrated narrower frequency range. Identification and analysis of these characteristics are required for effective remediation.     

Statistical methods in multi-speaker automatic speech recognition

Automatic speech recognition and understanding (ASR) plays an important role in the framework of man-machine communication. Substantial industrial developments are at present in progress in this area. However, after 40 years or so of efforts several fundamental questions remain open. This paper is concerned with a comparative study of four different methods for multi-speaker word recognition: (i) clustering of acoustic templates, (ii) comparison with a finite state automaton, (iii) dynamic programming and vector quantization, (iv) stochastic Markov sources. In order to make things comparable, the four methods were tested with the same material made up of the ten digits (0 to 9) pronounced four times by 60 different speakers (30 males and 30 females). We will distinguish in our experiments between multi-speaker systems (capable of recognizing words pronounced by speakers that have been used during the training phase of the system) and speaker-independent systems (capable of recognizing words pronounced by speakers totally unknown to the system). Half of the corpus (15 male and 15 female) were used for training, and the remaining part for test.     

隐马尔可夫模型在语音识别中的应用

隐马尔可夫模型 (HMM)的基本技术是语音识别中较为成功的算法 .主要是它具有较强的对时间序列结构的建模能力 .本文首先深入浅出地介绍了 HMM的基本技术和一个基于 HMM的孤立词语音识别系统的构成方法 ,其次 ,基于 HMM尚存有一些缺陷 ,造成语音识别能力较弱 ,为此本文又进一步阐述了语音识别应用中的几种改进的 HMM系统及目前的热点方法—— HMM与 ANN构成的混合网络     

汉语自然口语中声调识别的研究

汉语是一种带声调的语言，声调信息在汉语识别中具有非常重要的意义.传统的声调识别一般只研究朗读式语音中相对标准的声调，很少对声调调型比较复杂的自然口语进行专门的处理.针对汉语自然口语的特点，在声调建模单元的选择时提出了真实上下文的模型.同时，为了对声调模式进行精细建模，采用了一种层次聚类的方法来获得更多的声调模式.实验结果证明了方法的有效性. 关键词： 声调识别 自然口语 真实上下文模型 聚类     

语音技术在少数民族语言的应用研究

本文研讨缺乏语言资源的民族语言（如维吾尔语）中如何引用语音技术、开发应用系统问题．提出基于GMM-UBM混合SVM技术方法实现实用性说话人识别系统,通过小语料人工标注语音语料预选高精度声学根（seed）模型、再引导大语料训练生成鲁棒性声模提高连续语音识别精度实现汉民会话语音翻译系统．对维吾尔语70人发话电话语音识别实验结果显示,基于GMM-UBM -SVM方法的不特定说话人识别实验其正确识别率为94.3%,比先行GMM-UBM方法精度提升3%;基于seed声模HTK-Julius技术的维吾尔语连续语音识别实验,其识别率为72.5%,比直接使用语音文本对齐语料单靠HTK实现识别方法（63.2%）精度提高9.3%;同时本研究讨论基于Moses技术的汉维医院门诊会话语音翻译系统预测Blue值达到了57.7%．     

基于研究性学习的高校“化学史”课程改革与实践

基于研究性学习的理念,以化学专业本科生专业拓展课程“化学史”为研究对象,通过教师专题讲座、学生课堂演讲和课堂剧演出等形式进行了课程改革。实践结果表明,在检索化学史和化学各学科相关文献、确立话题、编制演讲稿或演出剧本、排练并进行演讲或演出的过程中,学生较好地体验了学科知识主动内化的过程,掌握了研究性学习的方法,培养了语言表达能力和团队协作能力,陶冶了科学情操并体会了科学品质和科学精神,有效提高了“化学史”课堂的学习兴趣和主动性。