Programming languages for fifth generation computers

Fifth Generation languages and computers, for use in the 1990's, may be based on significantly different concepts than traditional computing. There are four major categories of computing, each consisting of a programming style and corresponding computer. These are: procedural languages (and control flow computers); object-oriented languages (and actor computers); functional languages (and data flow or reduction computers); and logic languages (and logic computers). In the future any of these categories of languages may become “main-stream” programming styles. In this paper we briefly present these novel programming languages and examine their advantages and disadvantages for programming.     

Application of prosody models for developing speech systems in Indian languages

In this paper we demonstrate the use of prosody models for developing speech systems in Indian languages. Duration and intonation models developed using feedforward neural networks are considered as prosody models. Labelled broadcast news data in the languages Hindi, Telugu, Tamil and Kannada is used for developing the neural network models for predicting the duration and intonation. The features representing the positional, contextual and phonological constraints are used for developing the prosody models. In this paper, the use of prosody models is illustrated using speech recognition, speech synthesis, speaker recognition and language identification applications. Autoassociative neural networks and support vector machines are used as classification models for developing the speech systems. The performance of the speech systems has shown to be improved by combining the prosodic features along with one popular spectral feature set consisting of Weighted Linear Prediction Cepstral Coefficients (WLPCCs).     

An Automatic System for Detecting Prosodic Prominence in American English Continuous Speech

A precise identification of prosodic phenomena and the construction of tools able to properly manage such phenomena are essential steps to disambiguate the meaning of certain utterances. In particular they are useful for a wide variety of tasks: automatic recognition of spontaneous speech, automatic enhancement of speech-generation systems, solving ambiguities in natural language interpretation, the construction of large annotated language resources, such as prosodically tagged speech corpora, and teaching languages to foreign students using Computer Aided Language Learning (CALL) systems. This paper presents a study on the automatic detection of prosodic prominence in continuous speech, with particular reference to American English, but with good prospects of application to other languages. Prosodic prominence involves two different prosodic features: pitch accent and stress accent. Pitch accent is acoustically connected with fundamental frequency (F0) movements and overall syllable energy, whereas stress exhibits a strong correlation with syllable nuclei duration and mid-to-high-frequency emphasis. This paper shows that a careful measurement of these acoustic parameters, as well as the identification of their connection to prosodic parameters, makes it possible to build an automatic system capable of identifying prominent syllables in utterances with performance comparable with the inter-human agreement reported in the literature. Two different prominence detectors were studied and developed: the first uses a training corpus to set up thresholds properly, while the second uses a pure unsupervised method. In both cases, it is worth stressing that only acoustic parameters derived directly from speech waveforms are exploited.     

英汉自动翻译电话系统的实现原理

８０年代以来，语音识别与合成，语音编码和实时传输、多语种机器翻译等关键技术的迅速发展，促进了自动翻译电话系统的研究和开发。     

Sichuan dialect speech recognition with deep LSTM network

In speech recognition research,because of the variety of languages,corresponding speech recognition systems need to be constructed for different languages.Especially in a dialect speech recognition system,there are many special words and oral language features.In addition,dialect speech data is very scarce.Therefore,constructing a dialect speech recognition system is difficult.This paper constructs a speech recognition system for Sichuan dialect by combining a hidden Markov model(HMM)and a deep long short-term memory(LSTM)network.Using the HMM-LSTM architecture,we created a Sichuan dialect dataset and implemented a speech recognition system for this dataset.Compared with the deep neural network(DNN),the LSTM network can overcome the problem that the DNN only captures the context of a fixed number of information items.Moreover,to identify polyphone and special pronunciation vocabularies in Sichuan dialect accurately,we collect all the characters in the dataset and their common phoneme sequences to form a lexicon.Finally,this system yields a 11.34%character error rate on the Sichuan dialect evaluation dataset.As far as we know,it is the best performance for this corpus at present.     

A waveform concatenation technique for text-to-speech synthesis

Designing text-to-speech systems capable of producing natural sounding speech segments in different Indian languages is a challenging and ongoing problem. Due to the large number of possible pronunciations in different Indian languages, a number of speech segments are needed to be stored in the speech database while a concatenative speech synthesis technique is used to achieve highly natural speech segments. However, the large speech database size makes it unusable for small hand held devices or human computer interactive systems with limited storage resources. In this paper, we proposed a fraction-based waveform concatenation technique to produce intelligible speech segments from a small footprint speech database. The results of all the experiments performed shows the effectiveness of the proposed technique in producing intelligible speech segments in different Indian languages even with very less storage and computation overhead compared to the existing syllable-based technique.     

TOWARD A COMMON STRUCTURAL LEVEL FOR SOFTWARE,DATABASE, AND KNOWLEDGE-BASED SYSTEMS

Abstract

Different languages, tools, and techniques are used for the development of software systems, including database and knowledge-based systems. Although underlying languages employ structuring concepts such as classification, modularization, generalization, and perspectives, these common concepts remain overshadowed by differing terminologies and notations, due to the separate histories of software engineering, databases, and knowledge representation. Currently the still more complex and ambitious requirements on software systems call for integrated solutions concerning software engineering environments. As a starting point toward integration, in this paper we aim at deriving a common structural level for software systems. To approach this goal we start by analyzing the human thought process on one hand and successfully applied structuring techniques on the other hand to derive a catalogue of 10 structuring concepts. Building on that, a self-contained language called SFW (structuring framework) is introduced to provide means for a general and uniform specification of the structure of software systems. SFW is aimed at providing a catalogue of reference for structuring concepts in today's languages as well as a suggestion to establish a uniform structural level in future approaches.     

The effect of code-mixing on accent identification accuracy

We investigate whether accent identification is more effective for English utterances embedded in a different language as part of a mixed code than for English utterances that are part of a monolingual dialogue. Our focus is on Xhosa and Zulu, two South African languages for which code-mixing with English is very common. In order to carry out our investigation, we extract English utterances from mixed-code Xhosa and Zulu speech corpora, as well as comparable utterances from an English-only corpus by Xhosa and Zulu mother-tongue speakers. Experiments using automatic accent identification systems show that identification is substantially more accurate for the utterances originating from the mixed-code speech. These findings are supported by a corresponding set of perceptual experiments in which human subjects were asked to identify the accents of recorded utterances. We conclude that accent identification is more successful for these utterances because accents are more pronounced for English embedded in mother-tongue speech than for English spoken as part of a monolingual dialogue by non-native speakers. Furthermore we find that this is true for human listeners as well as for automatic identification systems.     

A visual environment for visual languages

The visual environment GENGED supports the visual definition of visual languages (VLs). Each VL is defined by an alphabet and a grammar. From a specific VL-definition, a VL-specification is generated which is the input of a graphical editor allowing for syntax-directed editing of diagrams over the specified VL. GENGED as well as each VL is based on the well-defined concepts of algebraic graph transformation and graphical constraint solving. The underlying formalism is hidden from the user, but it is essential for a formal presentation and manipulation of graphical structures. In this contribution, the GENGED concepts and environment are briefly proposed and illustrated by the definition of a simple kind of the well-known statechart language.     

Adding multidimensionality to procedural programming languages

One of the most serious shortcomings of multidimensional languages is their inability to collaborate with conventional programming languages and systems. Multidimensional languages are used to define (potentially infinite) streams, grids, cubes, and so on, concepts which resemble in nature the familiar imperative arrays. The main difference is that the former entities are lazy while the latter are generally eager. This paper proposes the embedding of multidimensional languages into conventional ones as a form of definitional lazy arrays. The paper describes the details of an implementation of the proposed idea, as well as the expressibility and the performance of the resulting system. The main advantage of the new approach is that multidimensional languages can now benefit from the advanced features that have been developed for conventional languages. Moreover, multidimensionality adds to conventional languages the idea of lazy arrays, which in many cases offer significant advantages compared to the classical imperative arrays. Copyright © 1999 John Wiley & Sons, Ltd.     

Ontological and linguistic metamodelling revisited: A language use approach

ContextAlthough metamodelling is generally accepted as important for our understanding of software and systems development, arguments about the validity and utility of ontological versus linguistic metamodelling continue.ObjectiveThe paper examines the traditional, metamodel-focused construction of modelling languages in the context of language use, and particularly speech act theory. These concepts are then applied to the problems introduced by the “Orthogonal Classification Architecture” that is often called the ontological/linguistic paradox. The aim of the paper is to show how it is possible to overcome these problems.MethodThe paper adopts a conceptual–analytical approach by revisiting the published arguments and developing an alternative metamodelling architecture based on language use.ResultsThe analysis shows that when we apply a language use perspective of meaning to traditional modelling concepts, a number of incongruities and misconceptions in the traditional approaches are revealed – issues that are not evident in previous work based primarily on set theory. Clearly differentiating between the extensional and intensional aspects of class concepts (as sets) and also between objects (in the social world) and things (in the physical world) allows for a deeper understanding to be gained of the relationship between the ontological and linguistic views promulgated in the modelling world.ConclusionsWe propose that a viewpoint that integrates language use ideas into traditional modelling (and metamodelling) is vital, and stress that meaning is not inherent in the physical world; meaning, and thus socially valid objects, are constructed by use of language, which may or may not establish a one-to-one correspondence relationship between objects and physical things.     

Enriching the conceptual basis for query formulation through relationship semantics in databases

The rapid increase in end-user computing calls into question the suitability of existing database query languages (DBQLs). Because the typical DB end-user is not a DB specialist, it is essential that DBQLs use concepts that are as close as possible to those in the end-users’ cognitive mental model and adopt interface techniques that are suited to end-users’ abilities. Concept-based query languages are well suited for this. This realization has motivated further research in conceptual, or semantic, query approaches. However, the primary focus in this field has been on semantic query optimization, not on query formulation. In this study, we address ourselves to the problem of formulation of queries using concepts. We propose a concept-based query language, called the conceptual query language (CQL), which allows for the conceptual abstraction of database queries and exploits the rich semantics of data models to ease and facilitate query formulation.The CQL approach uses the relationship semantics of semantic data models to render transparent the technical complexities of existing DB query languages. Association semantics are also used to automatically construct query graphs and pseudo-natural language explanations of queries, and to generate SQL codes. A set theoretic formalism for conceptual queries is developed and used. This paper discusses the design of CQL, its expressive power, its implementation, and the strategies for CQL query processing. The implementation of a CQL prototype is briefly discussed in this paper. User experiments were carried out extensively and showed the advantage of CQL over alternative languages such as SQL.     

Flexible speech translation systems

Speech translation research has made significant progress over the years with many high-visibility efforts showing that translation of spontaneously spoken speech from and to diverse languages is possible and applicable in a variety of domains. As language and domains continue to expand, practical concerns such as portability and reconfigurability of speech come into play: system maintenance becomes a key issue and data is never sufficient to cover the changing domains over varying languages. In this paper, we discuss strategies to overcome the limits of today's speech translation systems. In the first part, we describe our layered system architecture that allows for easy component integration, resource sharing across components, comparison of alternative approaches, and the migration toward hybrid desktop/PDA or stand-alone PDA systems. In the second part, we show how flexibility and reconfigurability is implemented by more radically relying on learning approaches and use our English-Thai two-way speech translation system as a concrete example.     

A survey of modeling language specification techniques

Visual modeling languages such as the Business Process Model and Notation and the Unified Modeling Language are widely used in industry and academia for the analysis and design of information systems. Such modeling languages are usually introduced in overarching specifications which are maintained by standardization institutions such as the Object Management Group or the Open Group. Being the primary – often the single – source of information, such specifications are of paramount importance for modelers, researchers, and tool vendors. However, structure, content, and specification techniques of such documents have never been systematically analyzed. This paper addresses this gap by reporting on a Systematic Literature Review aimed to analyze published standard modeling language specifications. In total, eleven specifications were found and comprehensively analyzed. The survey reveals heterogeneity in: (i) the modeling language concepts being specified, and (ii) the techniques being employed for the specification of these concepts. The identified specification techniques are analyzed and presented by referring to their utilization in the specifications. This survey provides a foundation for research aiming to increase consistency and improve comprehensiveness of information systems modeling languages.     

Web service集成标记语言关键技术研究

描述Web service的标记语言在使服务能被人们或软件Agents动态发现方面发挥着重要的作用。学术界和工业界研究小组在服务描述、发现、集成、执行上推出了很多基于XML结构的语言。这些语言中有些已经定义了良好的语义,有些是基于工作流方式的,同时也有一小部分是综合利用其它几个独立的语言而形成。面对这么多都被推荐成为标准的语言,对它们的优点和缺点作深入的分析是十分必要的。本文首先从便于服务描述、发现、集成和执行的角度,分析了Web service集成标记语言所应具有的特性,如表达性、语义支持、可用的支持工具、核心集成机制、对容错及异常处理的支持;然后简要描述了比较熟悉的几种服务集成语言的相关技术;最后对这些语言的关键特性作了比较。     

Language and Gender Classification of Speech Files Using Supervised Machine Learning Methods

Many language identification (LID) systems are based on language models using techniques that consider the fluctuation of speech over time. Considering these fluctuations necessitates longer recording intervals to obtain reasonable accuracy. Our research extracts features from short recording intervals to enable successful classification of spoken language. The feature extraction process is based on frames of 20 ms, whereas most previous LIDs presented results based on much longer frames (3?s or longer). We defined and implemented 200 features divided into four feature sets: cepstrum features, RASTA features, spectrum features, and waveform features. We applied eight machine learning (ML) methods on the features that were extracted from a corpus containing speech files in 10 languages from the Oregon Graduate Institute (OGI) telephone speech database and compared their performances using extensive experimental evaluation. The best optimized classification results were achieved by random forest (RF): from 76.29% on 10 languages to 89.18% on 2 languages. These results are better or comparable to the state-of-the-art results for the OGI database. Another set of experiments that was performed was gender classification from 2 to 10 languages. The accuracy and the F measure values for the RF method for all the language experiments were greater than or equal to 90.05%.     

A survey of systems programming languages: Concepts and facilities

In recent years, high-level programming languages have evolved specifically for systems programming. In this paper, systems programming languages are surveyed to find common characteristics and individual differences and limitations of a number of current languages, including Ada, Concurrent Pascal, CLU, Pascal-Plus, Modula-2, Mesa, Edison, PLZ/SYS and C. The survey is based on the following classification of systems programming concepts and facilities: types, sequential control, concurrency, encapsulation, environment specifications and programming support environments.     

Information flow and interconnections in computing: extensions and applications of Rent's rule

Rent's rule and related concepts of connectivity such as dimensionality, line-length distributions, and separators are discussed. Generalizations for systems for which the Rent exponent is not constant throughout the interconnection hierarchy are provided. The origin of Rent's rule is stressed as resulting from the embedding of a high-dimensional information flow graph to two- or three-dimensional physical space. The applicability of these concepts to free-space optically interconnected systems is discussed. The role of Rent's rule in fundamental studies of different interconnection media, including superconductors and optics, is briefly reviewed.     

Image-based features for speech signal classification

Like other applications, under the purview of pattern classification, analyzing speech signals is crucial. People often mix different languages while talking which makes this task complicated. This happens mostly in India, since different languages are used from one state to another. Among many, Southern part of India suffers a lot from this situation, where distinguishing their languages is important. In this paper, we propose image-based features for speech signal classification because it is possible to identify different patterns by visualizing their speech patterns. Modified Mel frequency cepstral coefficient (MFCC) features namely MFCC- Statistics Grade (MFCC-SG) were extracted which were visualized by plotting techniques and thereafter fed to a convolutional neural network. In this study, we used the top 4 languages namely Telugu, Tamil, Malayalam, and Kannada. Experiments were performed on more than 900 hours of data collected from YouTube leading to over 150000 images and the highest accuracy of 94.51% was obtained.