Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

/pdf/pomdp-based-statistical-spoken-dialog-systems-a-review-52td9wfczr.pdf

POMDP-Based Statistical Spoken Dialog Systems: A Review

EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark.

/pdf/julius-an-open-source-real-time-large-vocabulary-recognition-53pzd2d9jn.pdf

Julius --- An Open Source Real-Time Large Vocabulary Recognition Engine

This paper presents a comprehensive review of the industrial applications of artificial neural networks (ANNs), in the last 12 years. Common questions that arise to practitioners and control engineers while deciding how to use NNs for specific industrial tasks are answered. Workable issues regarding implementation details, training and performance evaluation of such algorithms are also discussed, based on a judiciously chronological organization of topologies and training methods effectively used in the past years. The most popular ANN topologies and training methods are listed and briefly discussed, as a reference to the application engineer. Finally, ANN industrial applications are grouped and tabulated by their main functions and what they actually performed on the referenced papers. The authors prepared this paper bearing in mind that an organized and normalized review would be suitable to help industrial managing and operational personnel decide which kind of ANN topology and training method would be adequate for their specific problems.

A comprehensive review for industrial applicability of artificial neural networks

Within the broad field of spoken dialogue systems, the application of machine-learning approaches to dialogue management strategy design is a rapidly growing research area. The main motivation is the hope of building systems that learn through trial-and-error interaction what constitutes a good dialogue strategy. Training of such systems could in theory be done using human users or using corpora of human–computer dialogue, but in practice the typically vast space of possible dialogue states and strategies cannot be explored without the use of automatic user simulation tools.This requirement for training statistical dialogue models has created an interesting new application area for predictive statistical user modelling and a variety of different techniques for simulating user behaviour have been presented in the literature ranging from simple Markov models to Bayesian networks. The development of reliable user simulation tools is critical to further progress on automatic dialogue management design but it holds many challenges, some of which have been encountered in other areas of current research on statistical user modelling, such as the problem of ‘concept drift’, the problem of combining content-based and collaboration-based modelling techniques, and user model evaluation. The latter topic is of particular interest, because simulation-based learning is currently one of the few applications of statistical user modelling that employs both direct ‘accuracy-based’ and indirect ‘utility-based’ evaluation techniques.In this paper, we briefly summarize the role of the dialogue manager in a spoken dialogue system, give a short introduction to reinforcement-learning of dialogue management strategies and review the literature on user modelling for simulation-based strategy learning. We further describe recent work on user model evaluation and discuss some of the current research issues in simulation-based learning from a user modelling perspective.

/pdf/a-survey-of-statistical-user-simulation-techniques-for-vxrq5a2bd4.pdf

A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategies

Old and new algorithms for the Maximum Satisfiability problem are studied We first summarize the different heuristics previously proposed, ie, the approximation algorithms of Johnson and of Lieberherr for the general Maximum Satisfiability problem, and the heuristics of Lieberherr and Specker, Poljak and Turzik for the Maximum 2-Satisfiability problem We then consider two recent local search algorithmic schemes, the Simulated Annealing method of Kirkpatrick, Gelatt and Vecchi and the Steepest Ascent Mildest Descent method, and adapt them to the Maximum Satisfiability problem The resulting algorithms, which avoid being blocked as soon as a local optimum has been found, are shown empirically to be more efficient than the heuristics previously proposed in the literature

Algorithms for the maximum satisfiability problem

This paper describes the method and the system investigated to solve the problem encountered in the automatic recognition of speech sound. From research in the automatic analyzer of speech sound, a monosyllable recognition system was constructed in which the phoneme is used as the basic recognition unit. Recently this system has been developed to accept the conversational speech sound with unlimited vocabulary. The mechanical recognition of conversational speech sound requires two basic operations. One is the segmentation of the continuous speech sound into several discrete intervals (or segments), each of which may be thought to correspond to a phoneme, and the other is the pattern recognition of such segments. For segmentation, by defining two criteria, ``stability'' and ``distance,'' the properties of the time pattern obtained by the analysis of input speech sound may be examined. The principle of the recognition is based on the mechanism of the articulation in our speech organ. Corresponding to this, the machine has the functions called phoneme classification, vowel analysis and consonant analysis. A conversational speech recognition system with the phonetic contextual approach is also applied to the vowel recognition where the time pattern of input speech is matched with the stored standard patterns in which the phonetic contextual effects are taken into consideration. The time pattern which has great variety may be effectively expressed by the new representation of ``sequential pattern'' and ``weighting pattern.''

The Automatic Speech Recognition System for Conversational Sound

This paper describes the understanding process of the spatial descriptions in Japanese. In order to understand the described world, the authors try to reconstruct the geometric model of the global scene from the scenic descriptions drawing a space. It is done by an experimental computer program SPRINT, which takes natural language texts and produces a model of the described world. To reconstruct the model, the authors extract the qualitative spatial constraints from the text, and represent them as the numerical constraints on the spatial attributes of the eutities. This makes it possible to express the vagueness of the spatial concepts and to derive the maximally plausible interpretation from a chunk of information accumulated as the constraints. The interpretation reflects the temporary belief about the world.

Reconstructing spatial image from natural language texts

The Phonetic Typewriter.

Intuitively, discontinuous changes can be seen as very rapid continuous changes. A couple of alternative methods based on this ontology are presented and compared. One, called the approximation method, approximates discontinuous change by continuous function and then calculates a limit. The other, called the direct method, directly creates a chain of hypothetical intermediate states (mythical instants) which a given circuit is supposed to go through during a discontinuous change. Although the direct method may fail to predict certain properties of discontinuity and its applicability is limited, it is more efficient than the approximation method. The direct method has been fully implemented and incorporated into an existing qualitative reasoning program.

Reasoning about discontinuous change

This paper describes the method and the system investigated to solve the problem encountered in the automatic recognition of speech sound From research in the automatic analyzer of speech sound, a monosyllable recognition system was constructed in which the phoneme is used as the basic recognition unit Recently this system has been developed to accept the conversational speech sound with unlimited vocabulary The mechanical recognition of conversational speech sound requires two basic operations One is the segmentation of the continuous speech sound into several discrete intervals (or segments), each of which may be thought to correspond to a phoneme, and the other is the pattern recognition of such segments For segmentation, by defining two criteria, ``stability'' and ``distance,'' the properties of the time pattern obtained by the analysis of input speech sound may be examined The principle of the recognition is based on the mechanism of the articulation in our speech organ Corresponding to this, the machine has the functions called phoneme classification, vowel analysis and consonant analysis A conversational speech recognition system with the phonetic contextual approach is also applied to the vowel recognition where the time pattern of input speech is matched with the stored standard patterns in which the phonetic contextual effects are taken into consideration The time pattern which has great variety may be effectively expressed by the new representation of ``sequential pattern'' and ``weighting pattern''

/pdf/the-automatic-speech-recognition-system-for-conversational-4tj9lgox95.pdf

Shuji Doshita

Papers

The Automatic Speech Recognition System for Conversational Sound

Reconstructing spatial image from natural language texts

The Phonetic Typewriter.

Reasoning about discontinuous change

The Automatic Speech Recognition System for Conversational Sound