基于语音生成和发音模型的语音合成新方法的探讨

提出基于语音生成模型和发音模型ＲＴＬＡ合成模式实现以共振峰轨迹为目标的语音合成的新方法。该方法采用了基于发音声学原理的反射型传输线模型来实现语音合成器。用于控制合成器的声道面积函数参数由以三个共振峰轨迹为目标的语音生成逆向解获得。该方法不仅可以得到动态过渡和自然度好的合成语音,能够方便灵活地控制或改变语音音色,合成器所需的输入控制参数少,参数更新率低。     

汉语多功能语音合成器

本文介绍了一种实用的汉语语音合成系统，本系统采用线性预测方法对语音信号进行分析与合成，并对码本进行矢量量化，码率压缩到1200bit／s，大幅度降低了语音的存储能量，合成出的语音仍具有较高的清晰度．这种以数字信号处理专用芯片TMS320C10为处理器的便携式语音合成器，合成语音数量大，成本低，功耗较小，既可联机使用，也可用电池供电，自成系统．实际应用证明，汉语多功能语音合成器实用性强，用途广泛，适于推广．     

汉语重音的凸显度分析与合成

重音是重要的语调特征,重音合成技术可以提高语音的自然度和表现力。针对重音的局部凸显性,该文提出了声学特征凸显度的表示方法,分析了不同韵律位置(韵律词首、中、尾,韵律短语首、中、尾等)重音音节的声学特征凸显度,发现在韵律单元末(韵律词末音节和韵律短语末韵律词)的重音其基频最大值凸显度要低于非韵律单元末重音,提出了基于声学特征凸显度的非线性的重音声学参数生成算法,解决了传统重音声学参数线性修改算法的修改幅度不足或过大的问题。采用该算法建立了基于隐Markov模型的支持重音合成的语音合成系统。实验表明,该系统可以有效合成带有重音的语音,提高了合成语音的自然度和表现力。      

汉语重音的凸显度分析与合成

重音是重要的语调特征,重音合成技术可以提高语音的自然度和表现力。针对重音的局部凸显性,该文提出了声学特征凸显度的表示方法,分析了不同韵律位置(韵律词首、中、尾,韵律短语首、中、尾等)重音音节的声学特征凸显度,发现在韵律单元末(韵律词末音节和韵律短语末韵律词)的重音其基频最大值凸显度要低于非韵律单元末重音,提出了基于声学特征凸显度的非线性的重音声学参数生成算法,解决了传统重音声学参数线性修改算法的修改幅度不足或过大的问题。采用该算法建立了基于隐Markov模型的支持重音合成的语音合成系统。实验表明,该系统可以有效合成带有重音的语音,提高了合成语音的自然度和表现力。     

粤语文语转换系统研究

由于计算机辅助数学(CAI)发展的需要,我们基于IBM系列微机,建立了一个粤语(广州话)文语转换系统。通过对粤语发音规律及语音参数的研究,此系统应用了共振峰参数语音合成技术,以无调音节和声调模式为基本合成单元,从自然语流中提取每个音节的共振峰语音参数并建立了供合成用的语音参数库。为实现计算机上的文语转换,自行编制了语音管理程序。此系统实现了国家一、二级汉字的广州话读音。日、英、俄文字母的发音及若干科学符号的广州话读音。且实现了计算机显示及相应发音的自由控制。     

汉语语音合成系统评价方法

从1994年开始，对汉语语音合成系统的工作性能定期举行全国评测．采用语言清晰度测试方法，1994年对五个不同的合成系统进行了评测和诊断．听音人为16名大学生（男8，女8），对合成言语没有经验．听音人响应是开放的听音记录．同时，还采用十点主观评价（MOS）测定言语自然度．为给出各合成系统音段层的诊断信息，对合成语音的辅音知觉混淆矩阵进行了分析．借助于对比自然言语和合成言语在不同语言层次上清晰度试验得分间的统计关系，来考察合成系统韵律特征处理的缺陷．结果表明，采用上述方法可得到评测合成系统工作性能的稳定合理的指标．有关韵律特征的评价方法有待于进一步发展．     

一种新的磁共振图像处理流水线的设计与实现

磁共振图像的重建、后处理及可视化是磁共振成像（MRI）系统的重要组成部分.本文开发了一个新的用于磁共振图像重建、后处理及可视化的开源框架YAP（Yet Another Pipeline），利用此框架可以方便地构建图像处理流水线.与现有的一些其他开源框架相比，本文开发的框架具有如下特点：（1）采用基于接口的设计，可使用基于接口的插件对流水线的功能进行扩展；（2）允许用户使用编写脚本的方式构建图像处理流水线，编辑与修改流水线都很方便；（3）支持带有分支结构的流水线，便于流水线的构建与调试.目前，该框架已经在商用系统中获得了应用.     

结合注意力机制的改进U-Net网络在端到端语音增强中的应用

设计了一个适用于端到端语音增强的改进的U-Net (Attention Dilated Convolution U-Net,ADC-U-Net)网络模型.与基线U-Net网络相比,一方面通过加入空洞卷积减小由采样带来的信息损失;另一方面引入了注意力机制结构,结合了含噪语音更多的上下文信息,提取更深层次和更丰富的特征信息...     

基于LMA声道模型的语声合成新方法

介绍一种基于LMA（LogMagnitudeApproximate）声道模型的语音合成新方法．采用这种方法，合成系统不但具有更好的合成音质，对韵律参数的调整能力也大大增强．合成实验表明，新的系统在自然度和可懂度上均比以前显著提高．文中首先介绍了LMA滤波器的基本原理和合成器的构成方案，然后详细讨论了用它对韵律参数进行调整的方法．最后，以一个较为成功的PSOLA合成系统KDTALK－1为对比，给出了系统性能的定量评价．     

基于平均模型和误差削减网络的语音转换系统*

现阶段用于语音转换的深度学习方法多是通过使用大量的训练数据来生成高质量的语音。本文提出了一种基于平均模型和误差削减网络的语音转换框架,可用于有限数量的训练数据。首先,基于CBHG网络的平均模型使用排除源说话人和目标说话人的多说话人语音数据进行训练;然后,在有限数量的目标语音数据下对平均模型执行自适应训练;最后,提出一种误差削减网络,可以进一步改善转换后语音的质量。实验表明,所提出的语音转换框架可以灵活地处理有限的训练数据,并且在客观和主观评估方面均优于传统框架。     

Experimental study on the naturalness of synthetic speech

In the past 10 years a Chinese text-to-speech system including aphonetic library,static tone model and basic synthesis rules had been estab-lished in IAAS.The Chinese synthesis of unrestricted vocabulary had beenachieved,but further steps must be taken to improve the naturalness ofsynthesized Chinese.The effect of segmental and suprasegmental features ofsynthetic speech upon naturalness have been studied by use of subjective as-sessment method.The results show that the rhythm in time domain andcoarticulation occupy a basic position for improving the naturalness of synthet-ic speech.And the fundamental frequency curve decided by tone model onlysuit to synthesize short sentence of Chinese.If the synthesis of larger linguisticunit than simple sentence is considered,the fundamental frequency curveshould be carefully manipulated.This paper presents the experimental methodand results,and discusses the way how to improve the naturalness of syntheticChinese.     

Vocal quality factors: analysis, synthesis, and perception.

The purpose of this study was to examine several factors of vocal quality that might be affected by changes in vocal fold vibratory patterns. Four voice types were examined: modal, vocal fry, falsetto, and breathy. Three categories of analysis techniques were developed to extract source-related features from speech and electroglottographic (EGG) signals. Four factors were found to be important for characterizing the glottal excitations for the four voice types: the glottal pulse width, the glottal pulse skewness, the abruptness of glottal closure, and the turbulent noise component. The significance of these factors for voice synthesis was studied and a new voice source model that accounted for certain physiological aspects of vocal fold motion was developed and tested using speech synthesis. Perceptual listening tests were conducted to evaluate the auditory effects of the source model parameters upon synthesized speech. The effects of the spectral slope of the source excitation, the shape of the glottal excitation pulse, and the characteristics of the turbulent noise source were considered. Applications for these research results include synthesis of natural sounding speech, synthesis and modeling of vocal disorders, and the development of speaker independent (or adaptive) speech recognition systems.     

Analysis, synthesis, and perception of voice quality variations among female and male talkers

Voice quality variations include a set of voicing sound source modifications ranging from laryngealized to normal to breathy phonation. Analysis of reiterant imitations of two sentences by ten female and six male talkers has shown that the potential acoustic cues to this type of voice quality variation include: (1) increases to the relative amplitude of the fundamental frequency component as open quotient increases; (2) increases to the amount of aspiration noise that replaces higher frequency harmonics as the arytenoids become more separated; (3) increases to lower formant bandwidths; and (4) introduction of extra pole zeros in the vocal-tract transfer function associated with tracheal coupling. Perceptual validation of the relative importance of these cues for signaling a breathy voice quality has been accomplished using a new voicing source model for synthesis of more natural male and female voices. The new formant synthesizer, KLSYN88, is fully documented here. Results of the perception study indicate that, contrary to previous research which emphasizes the importance of increased amplitude of the fundamental component, aspiration noise is perceptually most important. Without its presence, increases to the fundamental component may induce the sensation of nasality in a high-pitched voice. Further results of the acoustic analysis include the observations that: (1) over the course of a sentence, the acoustic manifestations of breathiness vary considerably--tending to increase for unstressed syllables, in utterance-final syllables, and at the margins of voiceless consonants; (2) on average, females are more breathy than males, but there are very large differences between subjects within each gender; (3) many utterances appear to end in a "breathy-laryngealized" type of vibration; and (4) diplophonic irregularities in the timing of glottal periods occur frequently, especially at the end of an utterance. Diplophonia and other deviations from perfect periodicity may be important aspects of naturalness in synthesis.     

Automatic acoustic synthesis of human-like laughter

A technique to synthesize laughter based on time-domain behavior of real instances of human laughter is presented. In the speech synthesis community, interest in improving the expressive quality of synthetic speech has grown considerably. While the focus has been on the linguistic aspects, such as precise control of speech intonation to achieve desired expressiveness, inclusion of nonlinguistic cues could further enhance the expressive quality of synthetic speech. Laughter is one such cue used for communicating, say, a happy or amusing context. It can be generated in many varieties and qualities: from a short exhalation to a long full-blown episode. Laughter is modeled at two levels, the overall episode level and at the local call level. The first attempts to capture the overall temporal behavior in a parametric model based on the equations that govern the simple harmonic motion of a mass-spring system is presented. By changing a set of easily available parameters, the authors are able to synthesize a variety of laughter. At the call level, the authors relied on a standard linear prediction based analysis-synthesis model. Results of subjective tests to assess the acceptability and naturalness of the synthetic laughter relative to real human laughter samples are presented.     

An approach to voice conversion using feature statistical mapping

The voice conversion (VC) technique recently has emerged as a new branch of speech synthesis dealing with speaker identity. In this work, a linear prediction (LP) analysis is carried out on speech signals to obtain acoustical parameters related to speaker identity - the speech fundamental frequency, or pitch, voicing decision, signal energy, and vocal tract parameters. Once these parameters are established for two different speakers designated as source and target speakers, statistical mapping functions can then be applied to modify the established parameters. The mapping functions are derived from these parameters in such a way that the source parameters resemble those of the target. Finally, the modified parameters are used to produce the new speech signal. To illustrate the feasibility of the proposed approach, a simple to use voice conversion software has been developed. This VC technique has shown satisfactory results. The synthesized speech signal virtually matching that of the target speaker.     

A text-to-speech system with high intelligibility and naturalness for Chinese

I.IntroductionResearchesonChinesesynthesisdisclosethatonlywhenboththesegmentalandsupraseg-melltalfeaturesofthesyntheticspeecharesimilartothoseofthellaturalone,thesyntheticspeechwillsoundintelligibleandnatural[1].Amongekistingsynthetictechniques,theapproachbasedonacousticparametersca-nadustboththesegmentalandsuprasegmentalfeaturesofsyntheticunitsfiekiblyandcanbeconsideredasthemostreasonablesynthetictechniqueintheory.However,theparameterbasedsynthesizerisoverAfependentonthedevelopmentsofparamet…     

Statistical analysis of bilingual speaker's speech for cross-language voice conversion.

The goal of cross-language voice conversion is to preserve the speech characteristics of one speaker when that speaker's speech is translated and used to synthesize speech in another language. In this paper, two preliminary studies, i.e., a statistical analysis of spectrum differences in different languages and the first attempt at a cross-language voice conversion, are reported. Speech uttered by a bilingual speaker is analyzed to examine spectrum difference between English and Japanese. Experimental results are (1) the codebook size for mixed speech from English and Japanese should be almost twice the codebook size of either English or Japanese; (2) although many code vectors occurred in both English and Japanese, some have a tendency to predominate in one language or the other; (3) code vectors that predominantly occurred in English are contained in the phonemes /r/, /ae/, /f/, /s/, and code vectors that predominantly occurred in Japanese are contained in /i/, /u/, /N/; and (4) judged from listening tests, listeners cannot reliably indicate the distinction between English speech decoded by a Japanese codebook and English speech decoded by an English codebook. A voice conversion algorithm based on codebook mapping was applied to cross-language voice conversion, and its performance was somewhat less effective than for voice conversion in the same language.     

Measuring the rate of change of voice fundamental frequency in fluent speech during mental depression

A method of measuring the rate of change of fundamental frequency has been developed in an effort to find acoustic voice parameters that could be useful in psychiatric research. A minicomputer program was used to extract seven parameters from the fundamental frequency contour of tape-recorded speech samples: (1) the average rate of change of the fundamental frequency and (2) its standard deviation, (3) the absolute rate of fundamental frequency change, (4) the total reading time, (5) the percent pause time of the total reading time, (6) the mean, and (7) the standard deviation of the fundamental frequency distribution. The method is demonstrated on (a) a material consisting of synthetic speech and (b) voice recordings of depressed patients who were examined during depression and after improvement.