Toward Robust Speech Recognition and Understanding

The principal cause of speech recognition errors is a mismatch between trained acoustic/language models and input speech due to the limited amount of training data in comparison with the vast variation of speech. It is crucial to establish methods that are robust against voice variation due to individuality, the physical and psychological condition of the speaker, telephone sets, microphones, network characteristics, additive background noise, speaking styles, and other aspects. This paper overviews robust architecture and modeling techniques for speech recognition and understanding. The topics include acoustic and language modeling for spontaneous speech recognition, unsupervised adaptation of acoustic and language models, robust architecture for spoken dialogue systems, multi-modal speech recognition, and speech summarization. This paper also discusses the most important research problems to be solved in order to achieve ultimate robust speech recognition and understanding systems. Dr. Sadaoki Furui is currently a Professor at Tokyo Institute of Technology, Department of Computer Science. He is engaged in a wide range of research on speech analysis, speech recognition, speaker recognition, speech synthesis, and multimodal human-computer interaction and has authored or coauthored over 450 published articles. From 1978 to 1979, he served on the staff of the Acoustics Research Department of Bell Laboratories, Murray Hill, New Jersey, as a visiting researcher working on speaker verification. He is a Fellow of the IEEE, the Acoustical Society of America and the Institute of Electronics, Information and Communication Engineers of Japan (IEICE). He was President of the Acoustical Society of Japan (ASJ) from 2001 to 2003 and the Permanent Council for International Conferences on Spoken Language Processing (PC-ICSLP) from 2000 to 2004. He is currently President of the International Speech Communication Association (ISCA). He was a Board of Governor of the IEEE Signal Processing Society from 2001 to 2003. He has served on the IEEE Technical Committees on Speech and MMSP and on numerous IEEE conference organizing committees. He has served as Editor-in-Chief of both Journal of Speech Communication and the Transaction of the IEICE. He is an Editorial Board member of Speech Communication, the Journal of Computer Speech and Language, and the Journal of Digital Signal Processing. He has received the Yonezawa Prize and the Paper Awards from the IEICE (1975, 88, 93, 2003), and the Sato Paper Award from the ASJ (1985, 87). He has received the Senior Award from the IEEE ASSP Society (1989) and the Achievement Award from the Minister of Science and Technology, Japan (1989). He has received the Technical Achievement Award and the Book Award from the IEICE (2003, 1990). He has also received the Mira Paul Memorial Award from the AFECT, India (2001). In 1993 he served as an IEEE SPS Distinguished Lecturer. He is the author of “Digital Speech Processing, Synthesis, and Recognition” (Marcel Dekker, 1989, revised, 2000) in English, “Digital Speech Processing” (Tokai University Press, 1985) in Japanese, “Acoustics and Speech Processing” (Kindai-Kagaku-Sha, 1992) in Japanese, and “Speech Information Processing” (Morikita, 1998) in Japanese. He edited “Advances in Speech Signal Processing” (Marcel Dekker, 1992) jointly with Dr. M.M. Sondhi. He has translated into Japanese “Fundamentals of Speech Recognition,” authored by Drs. L.R. Rabiner and B.-H. Juang (NTT Advanced Technology, 1995) and “Vector Quantization and Signal Compression,” authored by Drs. A. Gersho and R. M. Gray (Corona-sha, 1998).     

Decidable and undecidable logics with a binary modality

We give an overview of decidability results for modal logics having a binary modality. We put an emphasis on the demonstration of proof-techniques, and hope that this will also help in finding the borderlines between decidable and undecidable fragments of usual first-order logic.Research supported by the Hungarian National Foundation for Scientific Research grants no. T16448, F17452, T7255. Research of the first author is also supported by a grant of Logic Graduate School of Eötvös Loránd University Budapest     

多模噪声理论及其在通信保密中的应用

给出了一种比较通用的非高斯噪声模型——多模噪声,采用无惯性非线性变换器给出了多模噪声中信号的检测与估计方法,该方法对概率密度函数形状对称的噪声是普遍适用的。在此基础上设计了可用于通信保密的多模噪声,说明了本加密方法适用于无线通信信道加密,并从统计分析的角度研究了可能的密码分析方法。     

拥抱融合的多模态灾害分析算法

融合文本和图像的多模态信息相对于单模态可以提升灾害事件分析准确率。但是已有的工作多数将文本特征和图片特征进行简单的融合,在提取、融合特征的时候造成特征的冗余,同时忽略了模态之间的联系,没有考虑到图像和文本之间特征的相关性。为此,本文分析和研究目前流行的多模态融合算法,提出一种拥抱融合的多模态灾害事件分析算法。首先将文本特征和图像的特征向量互相对比,考虑文本和图像特征之间的相关性。然后基于多项抽样,剔除冗余的特征,融合文本特征和图像特征。实验结果表明,拥抱融合在CrisisMMD2.0数据集上实验1的2个任务的分类效果准确率分别高达88.2%、85.1%,都明显优于其他多模态融合模型,表明了该模型的有效性。同时第2个实验也验证了拥抱模型对于不同文本和图像深度学习模型的适用性。     

基于自适应联合字典学习的脑部多模态图像融合方法

针对目前全局训练字典对于脑部医学图像的自适应性不强,以及使用稀疏表示系数的L₁范数取极大的融合方式易造成图像的灰度不连续效应进而导致图像融合效果欠佳的问题,提出一种基于自适应联合字典学习的脑部多模态图像融合方法。该方法首先使用改进的K奇异值分解（K-SVD）算法自适应地从已配准的源图像中学习得到子字典并组合成自适应联合字典,在自适应联合字典的作用下由系数重用正交匹配追踪（CoefROMP）算法计算得到稀疏表示系数;然后将稀疏表示系数的"多范数"作为源图像块的活跃度测量,并提出"自适应加权平均"与"选择最大"相结合的无偏规则,根据稀疏表示系数的"多范数"的相似度选择融合规则,当"多范数"的相似度大于阈值时,使用"自适应加权平均"的规则,反之则使用"选择最大"的规则融合稀疏表示系数;最后根据融合系数与自适应联合字典重构融合图像。实验结果表明,与其他三种基于多尺度变换的方法和五种基于稀疏表示的方法相比,所提方法的融合图像能够保留更多的图像细节信息,对比度和清晰度较好,病灶边缘清晰,客观参数标准差、空间频率、互信息、基于梯度指标、基于通用图像质量指标和平均结构相似指标在三组实验条件下的均值分别为：71.0783、21.9708、3.6790、0.6603、0.7352和0.7339。该方法可以应用于临床诊断和辅助治疗。     

眼动-语言跨模态共指消解方法

跨模态共指消解是根据人员交互意图对自然图像中所指目标的定位任务,作为智能人机交互领域的关键技术之一,能够应用于抢险救灾、家庭服务或养老助残等场景。现有的目标指代方法一般采用单模态信息表现人类意图,例如语言或者眼动等,然而单一的模态用户输入只能够传达有限的交互信息,难以实现自然而智能的人机协同。本文针对这一问题,同时融合眼动和语言信息,建立了跨模态共指消解模型,利用多种模态信息的优势互补,实现人类意图所指目标的图像定位任务。设计了对比试验,验证了本文提出的眼动-语言跨模态的融合方法性能优于单模态的输入形式。     

移动设备生物特征识别多模态融合标准研究及展望

针对用于移动设备的生物特征识别多模态融合技术框架不统一以及标准缺失的问题,提出了多模态融合的分类、层级以及标准统一技术框架。首先分析国内外与移动设备生物特征识别相关的标准化现状;其次研究移动设备生物特征识别标准的本地识别以及远程识别应用模式,分析提出多特征、多算法、多实例、多传感器4种多模态融合分类方法,研究并提出样本级融合、特征级融合、分数级融合和决策级融合4种多模态融合的层级,并且提出用于移动设备的生物特征识别多模态融合标准技术框架;最后对移动设备生物特征识别多模态融合技术应用进行展望。     

A new filled function method for unconstrained global optimization

Many real world problems can be modelled as optimization problems. However, the traditional algorithms for these problems often encounter the problem of being trapped in local minima. The filled function method is an effective approach to tackle this kind of problems. However the existing filled functions have the disadvantages of discontinuity, non-differentiability or sensitivity to parameters which limit their efficiency. In this paper, we proposed a new filled function which is continuous and differentiable without any parameter to tune. Compared to discontinuous or non-differentiable filled functions, the continuous and differentiable filled function mainly has three advantages: firstly, it is not easier to produce extra local minima, secondly, more efficient local search algorithms using gradient information can be applied and thirdly, a continuous and differentiable filled function can be optimized more easily. Based on the new proposed filled function, a new algorithm was designed for unconstrained global optimization problems. Numerical experiments were conducted and the results show the proposed algorithm was more efficient.     

自适应免疫克隆选择算法的参数识别

提出了一种被称为是自适应免疫克隆选择算法的新型人工免疫算法,此方法可进行系统的参数识别,以解决结构的多目标优化问题.此种算法将二阶响应、适应性变异准则和疫苗因子这三种算子都引入到遗传克隆选择算法中,提高了运算的收敛速度及全局优化搜索能力.对动力系统参数识别的模拟识别结果证明了本文所提出算法的有效性与可行性.