Sisl: Several Interfaces, Single Logic

Modern interactive services such as information and e-commerce services are becoming increasingly more flexible in the types of user interfaces they support. These interfaces incorporate automatic speech recognition and natural language understanding and include graphical user interfaces on the desktop and web-based interfaces using applets and HTML forms. To what extent can the user interface software be decoupled from the service logic software (the code that defines the essential function of a service)? Decoupling of user interface from service logic directly impacts the flexibility of services, or how easy they are to modify and extend. To explore these issues, we have developed Sisl, an architecture and domain-specific language for designing and implementing interactive services with multiple user interfaces. A key principle underlying Sisl is that all user interfaces to a service share the same service logic. Sisl provides a clean separation between the service logic and the software for a variety of interfaces, including Java applets, HTML pages, speech-based natural language dialogue, and telephone-based voice access. Sisl uses an event-based model of services that allows service providers to support interchangeable user interfaces (or add new ones) to a single consistent source of service logic and data. As part of a collaboration between research and development, Sisl is being used to prototype a new generation of call processing services for a Lucent Technologies switching product.     

Improving Speech Recognition Accuracy for Small Vocabulary Applications in Adverse Environments

The problem of improving the accuracy of small vocabulary isolated word speaker dependent speech recognition under adverse conditions such as factory environments is considered. A new approach to solving this problem, by using Output Probability Distributions (OPDs), is presented. OPDs improve the system performance by modelling inter-word relationships, something that a standard maximum likelihood (ML) technique fails to do. The system was tested using the TI46 database, corrupted with the NOISEX-92 database, as well as in a real-world factory environment, and achieved good results.     

Initial Development Towards a Trilingual Speech Interface for Financial Information Inquiries

This paper describes our initial effort in developing a trilingual speech interface for financial information inquiries. Our foreign exchange inquiry system consists of: (i) monolingual and trilingual speech recognizers, which receive the user's spoken input in the form of microphone speech; (ii) a real-time data capture component which continuously updates a relational database from a financial data satellite feed; and (iii) a trilingual speech generation component, which generates English and Chinese text based on the raw financial data. The generated text is then transformed into spoken presentations. English text is processed by the FESTIVAL synthesizer system. Chinese text is sent to our syllable-based synthesizer, which employs a concatenative resequencing technique to produce spoken presentations in Putonghua or Cantonese. The speech interface is augmented with a visual display which aims to provide feedback to the user at all times during an interaction. Within the restricted scope of foreign exchange (FOREX), our recognition performance accuracies remain above 93%. Confusions across languages contributed significantly to our recognition errors, but most are confusions between the same currency/country names spoken in different languages. These errors are not detrimental with respect to data retrieval. Our concatenative re-sequencing technique reports the date, time and exchange rates of the input currency pair. A demonstration can be found at http://www.se.cuhk.edu.hk/hccl/demos/.     

Multiple expert classification: a new methodology for parallel decision fusion

Abstract. A new parallel hybrid decision fusion methodology is proposed. It is demonstrated that existing parallel multiple expert decision combination approaches can be divided into two broad categories based on the implicit decision emphasis implemented. The first category consists of methods implementing computationally intensive decision frameworks incorporating a priori information about the target task domain and the reliability of the participating experts, while the second category encompasses approaches implementing group consensus without assigning any importance to the reliability of the experts and ignoring other contextual information. The methodology proposed in this paper is a hybridisation of these two approaches and has shown significant performance enhancements in terms of higher overall recognition rates along with lower substitution rates. Detailed analysis using two different databases supports this claim. Received January 19, 1999 / Revised March 20, 2000     

Defect identification and sizing by the ultrasonic satellite-pulse technique

Shape and size are the most important defect characteristics that need to be determined for the reliable prediction of the remaining service lifetime of a defective structure or part. The analytical and supporting experimental results presented in this paper concern a general, pattern recognition-based, ultrasonic defect identification and sizing method. The satellite-pulse technique (SPT) is based on the interpretation, in terms of defect types (shapes) and dimensions, of the separation in time of arrival between the readily detected specularly reflected pulse and its generally ignored tip-diffracted or tangentially scattered satellite contained in the received waveform. Calibration procedures were also developed that enable the ultrasonic examiner to read the time scale of the oscilloscope for equivalent crack depth or void diameter as appropriate.     

基于指标权重的湖库营养状态识别

针对湖库营养状态识别未考虑指标权重及营养状态分级较少的不足,基于熵值法与概率神经网络（PNN）基本原理,提出熵值PNN湖库营养状态识别模型,以全国24个湖库营养状态识别为例进行分析。利用熵值法确定识别指标权重,依据我国湖库富营养化评价标准,将湖库营养状态划分为极贫营养一极重度富营养11个等级,提出基于改进的湖库营养状态识别等级标准,在等级标准域值间采用随机内插的方法生成样本对PNN模型进行训练和检验,利用正确识别率和运行时间对PNN模型性能进行评价。最后,基于两种方案对全国24个湖库营养状态进行识别。结果表明：@PNN模型对于随机生成的训练样本和检验样本的正确识别率分别达到98．9％、98．6％（5次平均）,模型用于湖库营养状态识别是合理可行的。②湖库识别结果存在差异。比较而言,基于指标权重考虑的识别结果更能科学、客观地反映湖库营养状态。     

An Inexpensive Digital Integrator for Gas Chromatography

SUMMARY

An inexpensive gas chromatographic integrator with digital readout is described. The device is precise to ±1 count and shows linear response to within ±2%. It is directly compatible with flame ionization detectors and is easily adapted to thermal conductivity detectors.     

轴承腔两相流动流型特征参数及鲁棒性分析

航空发动机轴承腔的润滑设计和换热分析依赖于对轴承腔中润滑介质两相流动特性的理解,依据流型进行轴承腔油气两相介质流动研究是获取流动特性的有效途径。针对通过试验判断油气两相介质流动形式的需要,结合数值分析和试验数据,在辨识能力和试验获取等方面的考虑前提下,提出了辨识航空发动机轴承腔中均相流动与含油滴气/液分层流动两种主要油气两相流型的特征参数——体积含油率和无量纲速度,探讨了两个特征参数在较宽工况范围内保持流型辨识能力的鲁棒性。研究工作对于借助于试验判断油气两相流型,从而可以在严谨理论指导下基于流型进行航空发动机轴承腔润滑介质两相流动特性分析,实现准确高效的润滑设计和换热分析的设计路线实施是很有意义的工作。     

一种改进的FSVM语音情感识别算法

针对语音特征参数对某类情感具有不确定性的问题,提出一种基于典型相关性分析的改进模糊支持向量机算法,应用于语音情感识别.采用典型相关性分析方法对特征向量进行降维,得到样本的约简向量集,在此约简向量集上建立模糊支持向量机模型判定情感类型.仿真实验结果表明,该方法相比于传统支持向量机法和模糊支持向量‘机法具有较高的识别准确率.