Synthesis and perception of breathy,normal, and Lombard speech in the presence of noise

This papers studies the synthesis of speech over a wide vocal effort continuum and its perception in the presence of noise. Three types of speech are recorded and studied along the continuum: breathy, normal, and Lombard speech. Corresponding synthetic voices are created by training and adapting the statistical parametric speech synthesis system GlottHMM. Natural and synthetic speech along the continuum is assessed in listening tests that evaluate the intelligibility, quality, and suitability of speech in three different realistic multichannel noise conditions: silence, moderate street noise, and extreme street noise. The evaluation results show that the synthesized voices with varying vocal effort are rated similarly to their natural counterparts both in terms of intelligibility and suitability.     

ProSynth: an integrated prosodic approach to device-independent,natural-sounding speech synthesis

This paper outlines ProSynth, an approach to speech synthesis which takes a rich linguistic structure as central to the generation of natural-sounding speech. We start from the assumption that the acoustic richness of the speech signal reflects linguistic structural richness and underlies the percept of naturalness. Naturalness achieved by paying attention to systematic phonetic detail in the spectral, temporal and intonational domains produces a perceptually robust signal that is intelligible in adverse listening conditions. ProSynth uses syntactic and phonological parses to model the fine acoustic–phonetic detail of real speech. We present examples of our approach to modelling systematic segmental, temporal and intonational detail and show how all are integrated in the prosodic structure. Preliminary tests to evaluate the effects of modelling systematic fine spectral detail, timing, and intonation suggest that the approach increases intelligibility and naturalness.     

A Methodology for Creating a Segment Inventory for Greek Time Domain Speech Synthesis

This article focuses on the systematic design of a segment database which has been used to support a time-domain speech synthesis system for the Greek language. Thus, a methodology is presented for the generation of a corpus containing all possible instances of the segments for the specific language. Issues such as the phonetic coverage, the sentence selection and iterative evaluation techniques employing custom-built tools, are examined. Emphasis is placed on the comparison of the process-derived corpus to naturally-occurring corpora with respect to their suitability for use in time-domain speech synthesis. The proposed methodology generates a corpus characterised by a near-minimal size and which provides a complete coverage of the Greek language. Furthermore, within this corpus, the distribution of segmental units is similar to that of natural corpora, allowing for the extraction of multiple units in the case of the most frequently-occurring segments. The corpus creation algorithm incorporates mechanisms that enable the fine-tuning of the segment database's language-dependent characteristics and thus assists in the generation of high-quality text-to-speech synthesis.     

Measuring the naturalness of synthetic speech

Even the highest quality synthetic speech generated by rule sounds unlike human sppech. As the intelligibility of rule-based synthetic speech improves, and the number of applications for synthetic speech increases, the naturalness of synthetic speech will become an important factor in determining its use. In order to improve this aspect of the quality of synthetic speech it is necessary to have diagnostic tests that can measure naturalness. Currently, all of the available metrics for evaluating the acceptability of synthetic speech do not distinguish sufficiently between measuring overall acceptability (including naturalness) and simply measuring the ability of listeners to extract intelligible information from the signal. In this paper we propose a new methodology for measuring the naturalness of particular aspects of synthesized speech, independent of the intelligibility of the speech. Although naturalness is a multidimensional, subjective quality of speech, this methodology makes it possible to assess the separate contributions of prosodic, segmental, and source characteristics of the utterance. In two experiments, listeners reliably differentiated the naturalness of speech produced by two male talkers and two text-to-speech systems. Furthermore, they reliably differentiated between the two text-to-speech systems. The results of these experiments demonstrate that perception of naturalness is affected by information contained within the smallest part of speech, the glottal pulse, and by information contained within the prosodic structure of a syllable. These results shown that this new methodology does provide a solid basis for measuring and diagnosing the naturalness of synthetic speech.     

低信噪比下高可懂度语音增强算法

提出了低信噪比下高可懂度的基于分段信噪比相对均方根（RMS）的语音增强子空间算法.现有的多数语音增强算法在低信噪比的恶劣条件下,改善带噪语音质量的同时通常会伴有语音可懂度的降低.一个重要原因是这些算法大都仅基于最小均方误差（MMSE）来抑制语音失真,却忽略了语音增强算法所导致的语音失真对差异类型语音分段的可懂度影响程度不同.为了改进这一缺点,提出了基于短时信噪比RMS对语音分段进行分类,然后调整处于信噪比中均方根语音分段的增益矩阵分量,来减小语音失真对增强语音可懂度的影响.客观评价实验说明,改进算法可以改善增强语音可懂度归一化协方差评价法（NCM）的评测值.主观试听实验说明,改进算法的确提升了增强后语音的可懂度.     

Syllable based text to speech synthesis system using auto associative neural network prosody prediction

This paper presents the design and development of an Auto Associative Neural Network (AANN) based unrestricted prosodic information synthesizer. Unrestricted Text To Speech System (TTS) is capable of synthesize different domain speech with improved quality. This paper deals with a corpus-driven text-to speech system based on the concatenative synthesis approach. Concatenative speech synthesis involves the concatenation of the basic units to synthesize an intelligent, natural sounding speech. A corpus-based method (unit selection) uses a large inventory to select the units and concatenate. The prosody prediction is done with the help of five layer auto associative neural network which helps us to improve the quality of speech synthesis. Here syllables are used as basic unit of speech synthesis database. The database consisting of the units along with their annotated information is called annotated speech corpus. A clustering technique is used in annotated speech corpus that provides way to select the appropriate unit for concatenation, based on the lowest total join cost of the speech unit. Discontinuities present at the unit boundaries are lowered by using the mel-LPC smoothing technique. The experiment has been made for the Dravidian language Tamil and the results reveal to demonstrate the improved intelligibility and naturalness of the proposed method. The proposed system is applicable to all the languages if the syllabification rules has been changed.     

Arabic speech synthesis and diacritic recognition

Text-to-speech system (TTS), known also as speech synthesizer, is one of the important technology in the last years due to the expanding field of applications. Several works on speech synthesizer have been made on English and French, whereas many other languages, including Arabic, have been recently taken into consideration. The area of Arabic speech synthesis has not sufficient progress and it is still in its first stage with a low speech quality. In fact, speech synthesis systems face several problems (e.g. speech quality, articulatory effect, etc.). Different methods were proposed to solve these issues, such as the use of large and different unit sizes. This method is mainly implemented with the concatenative approach to improve the speech quality and several works have proved its effectiveness. This paper presents an efficient Arabic TTS system based on statistical parametric approach and non-uniform units speech synthesis. Our system includes a diacritization engine. Modern Arabic text is written without mention the vowels, called also diacritic marks. Unfortunately, these marks are very important to define the right pronunciation of the text which explains the incorporation of the diacritization engine to our system. In this work, we propose a simple approach based on deep neural networks. Deep neural networks are trained to directly predict the diacritic marks and to predict the spectral and prosodic parameters. Furthermore, we propose a new simple stacked neural network approach to improve the accuracy of the acoustic models. Experimental results show that our diacritization system allows the generation of full diacritized text with high precision and our synthesis system produces high-quality speech.     

从音联出发设计语音库语料

语料设计是汉语语音库工作中的重要环节，本文从音联角度探讨汉语语音库的语料设计，提出用音联（包括闭音联、音节音联、节奏音联）来作为语料中音段声学信息载体，从音位实现角度，提出一种普通话音联分类方案，给出一些统计结果。本文还介绍了一种基于单联选词框架，它能在限定数据量大小的情况下，兼顾声母、韵母、音联以及无调音节等因素统计平衡。     

最佳相位设计的MBE声码器语音合成

提出了一种基于最佳相位设计的语音合成技术,能够有效降低MBE声码器合成语音信号由于波形失衡而导致的饱和失真的概率.此外,为了保证合成滤波器的稳定性,对线谱频率(LSF)系数提取进行了优化.实验结果显示,合成语音信号波形近似平衡地分布在零幅度值的上下,语音听起来没有不舒服的感觉.实验结果表明,基于最佳相位设计的语音合成技术能够有效改善合成语音质量.     

面向藏语语音合成的语音基元自动标注方法

在基于隐Markov模型（Hidden Markov Model,HMM）的统计参数藏语语音合成中引入了DAEM（Deterministic Annealing EM）算法,对没有时间标注的藏语训练语音进行自动时间标注。以声母和韵母为合成基元,在声母和韵母的声学模型的训练过程中,利用DAEM算法确定HMM模型的嵌入式重估的最佳参数。训练好声学模型后,再利用强制对齐自动获得声母和韵母的时间标注。实验结果表明,该方法对声母和韵母的时间标注接近手工标注的结果。对合成的藏语语音进行主观评测表明,该方法合成的藏语语音和手工标注声、韵母时间的方法合成的藏语语音的音质接近。因此,利用该方法可以在不需要声、韵母的时间标注的情况下建立合成基元的声学模型。     

Multi notch adaptive digital filter design for enhancement of speech signals embedded in non-stationary noise

This paper presents a new approach to speech enhancement based on modified least mean square-multi notch adaptive digital filter (MNADF). This approach differs from traditional speech enhancement methods since no a priori knowledge of the noise source statistics is required. Specifically, the proposed method is applied to the case where speech quality and intelligibility deteriorates in the presence of background noise. Speech coders and automatic speech recognition systems are designed to act on clean speech signals. Therefore, corrupted speech signals by the noise must be enhanced before their processing. The proposed method uses a primary input containing the corrupted speech signal and a reference input containing noise only. The new computationally efficient algorithm is developed here based on tracking significant frequencies of the noise and implementing MNADF at those frequencies. To track frequencies of the noise time-frequency analysis method such as short time frequency transform is used. Different types of noises from Noisex-92 database are used to degrade real speech signals. Objective measures, the study of the speech spectrograms and global signal-to-noise ratio (SNR), segmental SNR (segSNR) as well as subjective listing test demonstrate consistently superior enhancement performance of the proposed method over tradition speech enhancement method such as spectral subtraction.     

嵌入式语音合成系统中不定长单元技术

文中在原有嵌入式合成系统基础上引入不定长单元挑选、拼接技术提升系统语音合成效果的自然度，并且运用聚类算法对音库中不定长单元进行裁减，降低挑选算法的复杂度，减少系统的资源消耗，从而达到资源消耗和合成效果最佳平衡。     

Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions

Existing speech enhancement algorithms can improve speech quality but not speech intelligibility, and the reasons for that are unclear. In the present paper, we present a theoretical framework that can be used to analyze potential factors that can influence the intelligibility of processed speech. More specifically, this framework focuses on the fine-grain analysis of the distortions introduced by speech enhancement algorithms. It is hypothesized that if these distortions are properly controlled, then large gains in intelligibility can be achieved. To test this hypothesis, intelligibility tests are conducted with human listeners in which we present processed speech with controlled speech distortions. The aim of these tests is to assess the perceptual effect of the various distortions that can be introduced by speech enhancement algorithms on speech intelligibility. Results with three different enhancement algorithms indicated that certain distortions are more detrimental to speech intelligibility degradation than others. When these distortions were properly controlled, however, large gains in intelligibility were obtained by human listeners, even by spectral-subtractive algorithms which are known to degrade speech quality and intelligibility.     

Learning Prosodic Patterns for Mandarin Speech Synthesis

Higher quality synthesized speech is required for widespread use of text-to-speech (TTS) technology, and the prosodic pattern is the key feature that makes synthetic speech sound unnatural and monotonous, which mainly describes the variation of pitch. The rules used in most Chinese TTS systems are constructed by experts, with weak quality control and low precision. In this paper, we propose a combination of clustering and machine learning techniques to extract prosodic patterns from actual large mandarin speech databases to improve the naturalness and intelligibility of synthesized speech. Typical prosody models are found by clustering analysis. Some machine learning techniques, including Rough Set, Artificial Neural Network (ANN) and Decision tree, are trained for fundamental frequency and energy contours, which can be directly used in a pitch-synchronous-overlap-add-based (PSOLA-based) TTS system. The experimental results showed that synthesized prosodic features greatly resembled their original counterparts for most syllables.