维吾尔语中疑问和焦点对语调的共同调节作用

通过严格控制的语音实验,系统研究了维吾尔语焦点和疑问语气对语调的调节作用。结果发现维吾尔语疑问句中焦点对音高和时长都有调节作用:1)焦点词音高上升、音域扩大,焦点后音高仍保持高,但焦点前的音高基本不变; 2)疑问语调的重要特征是句末音高出现大幅度上扬,另外疑问句中焦点词后的音高高于其在陈述句条件下的表现; 3)焦点成分时长延长,而焦点前后成分的时长变化不明显; 4)与陈述句相比,疑问句的总时长要长于陈述句的,且主要表现在句末成分的时长上。总之,维吾尔语和汉语、英语一样支持平行编码目标逼近(PENTA)语调模型,但是三种语言在疑问句中焦点后的语调变化方式上并不相同。     

汉语韵律短语的时长与音高研究

语句和篇章的韵律结构和信息结构的分析及模型化是提高语音合成的自然度、降低自然语言识别错误率的关键。该文在带有韵律标注ASCCD语料库的基础上对韵律短语的时长和音高特性进行了研究,得到并验证了如下一些结论:(1)韵律短语边界对音节时长有明显的延长作用,不同声调对音节的时长延长作用不同,并且不同的重音级别对音节时长的延长作用也不同。(2)韵律短语边界处中断的时长在较小的韵律边界表现的更为明显。韵律短语的边界处发生了明显的音高重置现象,韵律短语的音高低线总是下降的,而音高高线只是在重音后下降,并且重音处的音域大而且音高高线的位置高。     

维吾尔语CVC型音节韵律特征声学分析

根据语音合成与识别等语音应用研究的需求,从实验语音学的角度出发,研究维吾尔语固有音节结构中最常见的CVC音节类型的声学特征,从“维吾尔语语音声学参数库”中选择1 255个CVC型音节的各种韵律参数,包括音节时长、音强和音高,进行统计分析并归纳其时长、音高和音强分布模式。     

维吾尔语三音节词韵律特征声学分析

本文从文本分析模块入手,利用“维吾尔语语音声学参数库”,选择了以开音节和闭音节结尾的333个三音节词的韵律参数,包括元音时长、音高和音强进行了统计分析,归纳了其元音时长、音高和音强分布模式,探讨了维吾尔语三音节词的韵律节奏模式与三音节词重音之间的关系问题,其目的是为了提高语音合成的自然度即更好的为自然语言处理服务。本项研究对维吾尔语语言乃至整个阿尔泰语系语言的韵律研究具有较高的参考价值。     

维吾尔语双音节词韵律特征声学分析

该文从文本分析模块入手,利用“维吾尔语语音声学参数库”,选择了以开音节和闭音节结尾的969个双音节词的韵律参数,包括元音时长、音高和音强进行了统计分析,归纳了其元音时长、音高和音强分布模式,探讨了维吾尔语双音节词的韵律节奏模式与双音节词重音之间的关系问题,其目的是为了提高语音合成的自然度。我们相信本项研究对维吾尔语语言乃至整个阿尔泰语系语言的韵律研究具有较高的参考价值。     

运用互信息匹配及关键词分析的语音对话系统

介绍应用于“虎丘,,旅游服务的非特定人语音对话系统.该系统运用互信息匹配模型MIM进行音节识别,并提出了关键词句法模型及相应的分析算法KBP进行语句分析和识别.实验表明,互信息匹配模型MIM的应用使连续语音音节识别率达到78%,而关键词句法分析的运用使系统总体语句识别率提高了65%,而且对预处理部分音节分割的误差以及不规范的语句输入有较好的容错处理能力.     

结合问题类型及惩罚机制的问题生成

问题生成旨在理解输入端的语义,从而自动生成疑问句。该文主要解决目标答案可知的问题生成任务,输入为陈述句和目标答案,输出为疑问句,该疑问句的答案为给定的目标答案。为了提高问题类型的准确率,使问句的表述更确切,该文提出一种融合问题类型及惩罚机制的问题生成模型,首先使用预训练BERT模型对问题类型进行分类,得到对应问题类型的表示。在编码端,通过门控机制将源端陈述句与问题类型进行融合,得到具有问题类型信息的源端表示。此外,在现有工作中观测到生成的问句和目标答案存在重复词的现象。为了缓解上述问题,该文提出一种惩罚机制,即在损失函数中加入对重复词的惩罚。实验证明,该文所提方法有效提高了问题类型的准确率,并在一定程度上降低了生成重复词的情况。在SQuAD数据集上BLEU-4值达到18.52%,问题类型的准确率达到93.46%。     

维吾尔语三音节词中元音和谐的声学特征分析

该文从提高语音合成自然度的实际需求出发,首次从实验语音学的角度从《维吾尔语语音声学参数库》中统计出了333个三音节词,其中再筛选了93个全和谐词和半和谐词,并对其元音的宽带共振峰模式、共振峰值、音高、时长和音强等韵律参数进行了统计分析,归纳了其共振峰、音高、时长和音强分布特点来考察元音和谐的基本声学特征,总结出了一些重要的规则和结论,为参数式或波形拼接式语音合成系统中调整合成前的元音和谐问题提供了重要的参考依据。     

可发多种方音调的语音合成系统

本文运用时域基音同步叠加的合成方法，用汉语普通语的无调音节库，合成出了包括普通话在内的五种地方官话腔调的合成语音；同时应用变调规则、轻志规则、音长规则和句型规则，对合成语句的音高和音长进行调整，改善了该语音合成系统输出语句的自然度。     

基于问句类型的问句相似度计算

目前,问句相似度的计算主要借鉴普通陈述句的相似度计算方法。由于普通陈述句的相似性更多反映的是语句间语义上的匹配符合程度,而衡量问句间的相似性则须同时考虑问句及其答案句之间的相似程度,为此,设计了一种新的问句相似度计算方法。该方法不仅利用问句之间的语义和语法特征考察问句之间的匹配程度,还利用问句的问题类型等信息来间接刻画答案句之间的特征形象,从而以获取问句的深层语义信息,以提高问句相似度计算的准确性。实验验证了该方法的有效性。     

Discovering salient prosodic cues and their interactions for automatic story segmentation in Mandarin broadcast news

This paper investigates speech prosody for automatic story segmentation in Mandarin broadcast news. Prosodic cues effectively used in English story segmentation deserve a re-investigation since the lexical tones of Mandarin may complicate the expressions of pitch declination and reset. Our data-oriented study shows that story boundaries cannot be clearly discriminated from utterance boundaries by speaker normalized pitch features due to their large variations across different Mandarin syllable tones. We thus propose to use speaker- and tone-normalized pitch features that can provide clear separations between utterance and story boundaries. Our study also shows that speaker-normalized pause duration is quite effective to separate between story and utterance boundaries, while speaker-normalized speech energy and syllable duration are not effective. Experiments using decision trees for story boundary detection reinforce the difference between English and Chinese, i.e., speaker- and tone-normalized pitch features should be favorably adopted in Mandarin story segmentation. We show that the combination of different prosodic cues can achieve a very high F-measure of 93.04% due to the complementarity between pause, pitch and energy. Analysis of the decision tree uncovered five major heuristics that show how speakers jointly utilize pause duration and pitch to separate speech into stories.     

iPEEH: Improving pitch estimation by enhancing harmonics

Pitch estimation is quite crucial to many applications. Although a number of estimation methods working in different domains have been put forward, there are still demands for improvement, especially for noisy speech. In this paper, we present iPEEH, a general technique to raise performance of pitch estimators by enhancing harmonics. By analysis and experiments, it is found that missing and submerged harmonics are the root causes for failures of many pitch detectors. Hence, we propose to enhance the harmonics in spectrum before implementing the pitch detection. One enhancement algorithm that mainly applies the square operation to regenerate harmonics is presented in detail, including the theoretical analysis and implementation. Four speech databases with 11 types of additive noise and 5 noise levels are utilized in assessment. We compare the performance of algorithms before and after using iPEEH. Experimental results indicate that the proposed iPEEH can effectively reduce the detection errors. In some cases, the error rate reductions are higher than 20%. In addition, the advantage of iPEEH is manifold since it is demonstrated in experiments that the iPEEH is effective for various noise types, noise levels, multiple basic frequency-based estimators, and two audio types. Through this work, we investigated the underlying reasons for pitch detection failures and presented a novel direction for pitch detection. Besides, this approach, a preprocessing step in essence, indicates the significance of preprocessing for any intelligent systems.     

Adaptive back-stepping pitch angle control for wind turbine based on a new electro-hydraulic pitch system

A new electro-hydraulic pitch system is proposed to smooth the output power and drive-train torque fluctuations for wind turbine. This new pitch system employs a servo-valve-controlled hydraulic motor to enhance pitch control performances. This pitch system is represented by a state-space model with parametric uncertainties and nonlinearities. An adaptive back-stepping pitch angle controller is synthesised based on this state-space model to accurately achieve the desired pitch angle control regardless of such uncertainties and nonlinearities. This pitch angle controller includes a back-stepping procedure and an adaption law to deal with such uncertainties and nonlinearities and hence to improve the final pitch control performances. The proposed pitch system and the designed pitch angle controller have been validated for achievable and efficient power and torque regulation performances by comparative experimental results under various operating conditions.     

Classification of speech signal based on gender: a hybrid approach using neuro-fuzzy systems

One of the most important processes in speech processing is gender classification. Generally gender classification is done by considering pitch as feature. In general the pitch value of female is higher than the male. In some cases, pitch value of male is higher and female is low, in that cases this classification will not obtain the exact result. By considering this drawback here proposed a gender classification method which considers three features and uses fuzzy logic and neural network to identify the given speech signal belongs to which gender. For training fuzzy logic and neural network, training dataset is generated by considering the above three features. After completion of training, a speech signal is given as input, fuzzy and neural network gives an output, for that output mean value is taken and this value gives the speech signal belongs to which gender. The result shows the performance of our method in gender classification.     

The Problem Statement is the Problem

A problem statement encouraging elegance is spare, unadorned, clean, and leaves the designer as much room as can be left. This is the hardest part of any design process. A good problem statement is a mentor and a supervisor. It asks the right question. A good problem statement extends its writer's skill and wisdom so that, if those are in short supply, the problem statement can make up for some of that itself.     

Synthesizing Transformations for Locality Enhancement of Imperfectly-Nested Loop Nests

Linear loop transformations and tiling are known to be very effective for enhancing locality of reference in perfectly-nested loops. However, they cannot be applied directly to imperfectly-nested loops. Some compilers attempt to convert imperfectly-nested loops into perfectly-nested loops by using statement sinking, loop fusion, etc., and then apply locality enhancing transformations to the resulting perfectly-nested loops, but the approaches used are fairly ad hoc and may fail even for simple programs. In this paper, we present a systematic approach for synthesizing transformations to enhance locality in imperfectly-nested loops. The key idea is to embed the iteration space of each statement into a special iteration space called the product space. The product space can be viewed as a perfectly-nested loop nest, so embedding generalizes techniques like statement sinking and loop fusion which are used in ad hoc ways in current compilers to produce perfectly-nested loops from imperfectly-nested ones. In contrast to these ad hoc techniques however, our embeddings are chosen carefully to enhance locality. The product space can itself be transformed to increase locality further, after which fully permutable loops can be tiled. The final code generation step may produce imperfectly-nested loops as output if that is desirable. We present experimental evidence for the effectiveness of this approach, using dense numerical linear algebra benchmarks, relaxation codes, and the tomcatv code from the SPEC benchmarks.     

基于基频特征的情感语音识别研究*

探索在不同的情感状态下的基音特征变化规律.通过对含有生气、高兴、悲伤情感语音信号进行分析,总结了情感语音基频的变化规律,确定了用于情感识别的12维的基频的基本特征以及扩展特征,运用混合高斯模型进行情感识别,并作了识别实验,获得了较好的结果.     

Evaluating software complexity measures

A set of properties of syntactic software complexity measures is proposed to serve as a basis for the evaluation of such measures. Four known complexity measures are evaluated and compared using these criteria. This formalized evaluation clarifies the strengths and weaknesses of the examined complexity measures, which include the statement count, cyclomatic number, effort measure, and data flow complexity measures. None of these measures possesses all nine properties, and several are found to fail to possess particularly fundamental properties; this failure calls into question their usefulness in measuring synthetic complexity