Consistency analysis of the spectrum and prosody within a syllable for Mandarin speech

This work presents a study of Mandarin speech focusing on consistency analysis of the spectrum and prosody within syllables. Identified as a result of inspection of the human pronunciation process, this consistency can be interpreted as a high correlation between the warping curves of the spectrum and the prosody intra a syllable. The consistency analysis consisted of three steps. First, the hidden Markov model algorithm was used to decode the hidden Markov model‐state sequences within a syllable, while at the same time dividing them into three segments. Second, based on a designated syllable, the vector quantization (VQ) with the Linde–Buzo–Gray algorithm was employed to train the VQ codebooks of the prosodic vector of each segment. Third, the prosodic vector of each segment was encoded as an index using the VQ codebooks, and then, to analyze the consistency, the probability of each possible path was evaluated as a prerequisite. Finally, two syllables were used as examples to verify the consistency property found in the experiments. It is demonstrated experimentally that there is definitely consistency in the case where the syllable is located in exactly the same word. These results offer a research direction in that the warping process between the spectrum and the prosody intra a syllable must be considered in text‐to‐speech systems to improve the synthesized speech quality. Copyright © 2013 John Wiley & Sons, Ltd.     

The Study of Full Light Speech Signal Collection System

1　Ｉｎｔｒｏｄｕｃｔｉｏｎ　　Ｏｐｔｉｃｆｉｂｅｒｃｏｕｐｌｅｒｓｈａｖｅｂｅｅｎｗｉｄｅｌｙｕｓｅｄｉｎｔｈｅｏｐｔｉｃａｌｃｏｍｍｕｎｉｃａｔｉｏｎａｎｄｏｐｔｉｃａｌｓｅｎｓｏｒｓ.Ｂｅｓｉｄｅｓｔｈｅｉｒｐｏｗｅｒｄｉｓｔｒｉｂｕｔｉｏｎｆｕｎｃｔｉｏｎｓ,ｔｈｅｃｏｕｐｌｅｒｓ′ｃｏｈｅｒｅｎｔｄｅｍｏｄｕｌａｔｉｏｎｃｈａｒａｃｔｅｒｗｈｉｃｈｈａｓｂｅｅｎｕｓｅｄｉｎｔｈｅｆｉｅｌｄｏｆｏｐｔｉｃｉｎｔｅｒｆｅｒｏｍｅｔｅｒ[1 ,2 ] ｉｓａｌｓｏｉｍｐｏｒｔａｎｔ,ｂｕｔｔｈａｔｗａｓ…     

低码率语音编码中过渡帧对合成语音的影响*

过渡段对语音清晰度、可懂度和人耳听觉感知都起到不可忽视的作用。参数语音编码中,包含有过渡段的语音帧能否得到恰当处理,是决定其合成语音是否清晰可懂的关键。本文以混合激励线性预测编码为参考,将其中的语音帧划分为静音、清音、浊音、过渡四大类后分别处理,在以往低码率语音编码(1 kbps)工作基础上,比较了八种过渡帧划分方法对合成语音PESQ MOS的影响。经分析后发现:不同的过渡帧对PESQ MOS的贡献也不同。由清、静音向浊音变化的过渡帧的贡献最大;介于浊辅音与元音之间的过渡帧的贡献也不应被忽略。     

语音识别技术在电子货架标签系统中的应用

目前卖场中电子货架标签的管理系统主要部署在计算机上,计算机位置相对固定,使用键盘、鼠标交互灵活性不高、操作效率有限,针对以上管理局限,提出了一个基于Android平台和语音识别技术的管理系统设计方案,以提高操作的便携性和工作效率。实验结果表明,该语音管理系统能够以较高的识别性能和操作效率实现对ESL的可移动声控管理,有利于电子货架标签的推广和应用,同时也为基于Android平台的语音识别系统在其他控制领域的应用提供了可供参考的案例和思路。     

基于听觉感知的语音稀疏表示及压缩感知*

本文针对语音信号稀疏表示及压缩感知问题,将听觉感知引入稀疏系数筛选过程,用掩蔽阈值筛选重要系数,以得到更符合听觉感受的语音稀疏表示。通过对一帧浊音信号分别采用掩蔽阈值和能量阈值方法进行系数筛选对比实验,结果表明掩蔽阈值法具有更好的稀疏表示效果。为验证听觉感知对语音压缩感知性能的影响,与能量阈值法对照对测试语音进行压缩感知观测和重构,通过压缩比、信噪比、主观平均意见分等主客观指标评价其性能,结果表明,掩蔽阈值法可有效地提高压缩比且保证重构语音具有较高的主观听觉质量。     

ODEON仿真与实际测量语言传输指数实验对比

近年来音质仿真技术的快速发展为语言传输指数STI的预测提供了一个潜在的解决方案。但这种方法的有效性如何,则是在使用该技术之前应该考虑的问题。本文对3个房间内音质仿真与实际测量STI进行实验对比,研究表明:在仿真模型与实际空间的声学等效较为准确的情况下,使用音质仿真软件ODEON计算得到的STI误差较小;混响时间的变化在背景噪声较高时可能会对仿真STI的准确性带来显著影响,随着混响时间的增加,仿真与实际测量STI的差值可能变大;信噪比的变化并不会给仿真STI的准确性带来显著影响;仿真脉冲响应与实际测量脉冲响应的频谱有一定差别,时域上的反射声序列也不相同,但这些差别对仿真STI的影响并不大;仿真过程中比较容易产生的信噪比误差对仿真STI产生了较大影响。由于影响音质仿真结果的因素较多,仿真模型与实际空间的声学等效也比较复杂,尤其是对于没有实际参照校准的房间来说,想要获得准确的STI预测结果是比较困难的。     

Disruption of writing by background speech: The role of speech transmission index

Speech transmission index (STI) is an objective measure of the acoustic properties of office environments and is used to specify norms for acceptable acoustic work conditions. Yet, the tasks used to evaluate the effects of varying STIs on work performance have often been focusing on memory (as memory of visually presented words) and reading tasks and may not give a complete view of the severity even of low STI values (i.e., when speech intelligibility is low). Against this background, we used a more typical office-work task in the present study. The participants were asked to write short essays (5 min per essay) in 5 different STI conditions (0.08; 0.23; 0.34; 0.50; and 0.71). Writing fluency dropped drastically and the number of pauses longer than 5 s increased at STI values above 0.23. This study shows that realistic work-related performance drops even at low STI values and has implications for how to evaluate acoustic conditions in school and office environments.     

Velopharyngeal aerodynamics of /m/ and /p/ in tracheoesophageal speech

The purpose of this study was to compare oral pressure (P_o), nasal airflow (V_n), and velopharyngeal (VP) orifice area estimates from 12 tracheoesophageal (TE) and 12 laryngeal speakers as they produced /p/ and /m/ in syllable series. The findings were as follows: (1) TE speakers produced greater P_o than the laryngeal speakers; (2) for /p/, TE speakers generated V_n, and VP orifice area estimates comparable with, or less than, the laryngeal speakers; and (3) for /m/, TE speakers had V_n and VP orifice area estimates greater than the laryngeal speakers. The elevated P_o could be the result of several factors such as high source driving pressures and vocal tract volume changes postlaryngectomy. Attempts at more precise articulation, and subsequently less coarticulation, by the TE speakers may explain the V_n and VP orifice area estimates for /p/ and /m/. TE speakers may be limiting the oral-nasal cavity coupling for /p/ (smaller VP gap, less V_n) in an attempt to produce a very precise oral /p/. For /m/, TE speakers may be attempting to overtly mark the consonant as a nasal (greater V_n, larger VP gap). Further studies are needed to confirm/refute the explanations postulated here regarding the VP aerodynamic differences that were identified.     

Contrastive analysis on tone between Putonghua and Taiwan Mandarin

The differences of the pitch and duration of Chinese syllables between Putonghua （PTH） and Taiwan Mandarin （TM） were studied. The speech materials to be used are not only isolated syllables, but also sentences. The results reveal that： For the isolated syllables, T1 and T2 in TM are influenced by Minnan dialect, therefore their pitch are lower than those in PTH. T3 is fall-rise in PTH, while it is fall in TM. Moreover, the syllable duration sequence for different tone is T3〉T2〉T1〉T4 in PTH, while it is T1〉T2〉T3〉T4 in TM. For the syllables in sentences, T2 is mid-rise in PTH, while it is mid-level in TM. And the T3 is longer than T4 but shorter than T1 or T2 in PTH, while it is the shortest in TM. Furthermore the effects of prosodic phrase boundary on duration for different tones are almost the same in PTH, but the lengthening part of T1 or T2 is longer than that of T3 or T4 in TM.