Voice communication between humans and machines / David B. Roe and Jay G. Wilpon, editors.

Format:

Book

Contributor:

Roe, David B.

Wilpon, Jay G.

National Academy of Sciences (U.S.)

Language:

English

Subjects (All):

Automatic speech recognition.

Human-machine systems.

Physical Description:

viii, 548 p. : ill.

Edition:

1st ed.

Place of Publication:

Washington, D.C. : National Academy Press, 1994.

Language Note:

English

Summary:

Science fiction has long been populated with conversational computers and robots. Now, speech synthesis and recognition have matured to where a wide range of real-world applications--from serving people with disabilities to boosting the nation's competitiveness--are within our grasp. Voice Communication Between Humans and Machines takes the first interdisciplinary look at what we know about voice processing, where our technologies stand, and what the future may hold for this fascinating field. The volume integrates theoretical, technical, and practical views from world-class experts at leading research centers around the world, reporting on the scientific bases behind human-machine voice communication, the state of the art in computerization, and progress in user friendliness. It offers an up-to-date treatment of technological progress in key areas: speech synthesis, speech recognition, and natural language understanding. The book also explores the emergence of the voice processing industry and specific opportunities in telecommunications and other businesses, in military and government operations, and in assistance for the disabled. It outlines, as well, practical issues and research questions that must be resolved if machines are to become fellow problem-solvers along with humans. Voice Communication Between Humans and Machines provides a comprehensive understanding of the field of voice processing for engineers, researchers, and business executives, as well as speech and hearing specialists, advocates for people with disabilities, faculty and students, and interested individuals.

Contents:

VOICE COMMUNICATION BETWEEN HUMANS AND MACHINES

Copyright

Acknowledgments

Contents

Voice Communication Between Humans and Machines-An Introduction

ELEMENTS OF VOICE PROCESSING TECHNOLOGY

VOICE CODING

VOICE SYNTHESIS

SPEECH RECOGNITION

SPEAKER RECOGNITION

SPOKEN LANGUAGE TRANSLATION

NATURAL LANGUAGE PROCESSING

COLLOQUIUM THEME

SCIENTIFIC BASES OF HUMAN-MACHINE COMMUNICATION BY VOICE

Scientific Bases of Human-Machine Communication by Voice

SUMMARY

INTRODUCTION

DIGITAL COMPUTATION AND MICROELECTRONICS

SPEECH ANALYSIS AND SYNTHESIS

SPEECH RECOGNITION AND UNDERSTANDING

USABILITY ISSUES

CONCLUSION

REFERENCES

The Role of Voice in Human-Machine Communication

Background and Definitions

Speech Analysis

Speech Synthesis

WHEN IS SPOKEN INTERACTION WITH COMPUTERS USEFUL?

Voice Input

Hands/Eyes-Busy Tasks

Limited Keyboard/Screen Option

Disability

Subject Matter Is Pronunciation

Voice Output

Summary

COMPARISON OF SPOKEN LANGUAGE WITH OTHER COMMUNICATION MODALITIES

Spoken Language System Prototypes

Spoken Language vs. Typed Language

Research Methodology

Comparison of Language-Based Communication Modalities

Comparison of Natural Language Interaction with Alternative Modalities

Direct Manipulation

Natural Language Interaction

Summary: Circumstances Favoring Spoken Language Interaction with Machines

HUMAN FACTORS OBSTACLES TO SPOKEN LANGUAGE SYSTEMS

Spontaneous Speech

Natural Language

Interaction and Dialogue

MULTIMODAL SYSTEMS

SCIENTIFIC RESEARCH ON COMMUNICATION MODALITIES

ACKNOWLEDGMENTS

Speech Communication-An Overview

FOUNDATIONS OF SPEECH TECHNOLOGY

INCENTIVES IN SPEECH RESEARCH

TECHNOLOGY STATUS

Coding.

Recognition and synthesis.

Talker verification.

Autodirective microphone arrays.

CRITICAL DIRECTIONS IN SPEECH RESEARCH

Physics of Speech Generation

Fluid-Dynamic Principles

Computational Models of Language

Information Processing in the Auditory System

Auditory Behavior

Coalescing Speech Coding, Synthesis, and Recognition

Robust" Techniques for Speech Analysis

Three Dimensional Sound Capture and Projection

Integration of Sensory Modalities for Sight, Sound, and Touch

SPEECH TECHNOLOGY PROJECTIONS-2000

BIBLIOGRAPHY

SPEECH SYNTHESIS TECHNOLOGY

Computer Speech Synthesis: Its Status and Prospects

Models of Speech Synthesis

Knowledge About Natural Speech

Flexibility and Technical Dimensions

The Sound-Generating Part

Simple Waveform Concatenation

Analysis-Synthesis Systems

Source Models

Formant-Based Terminal Analog

Higher-Level Parameters

Articulatory Models

THE CONTROL PART

Concatenation of Units

Rules and Notations

Automatic Learning

SPEAKING CHARACTERISTICS AND SPEAKING STYLES

MULTILINGUAL SYNTHESIS

Speech Quality

CONCLUDING REMARKS

Linguistic Aspects of Speech Synthesis

CONSTRAINTS ON SPEECH PRODUCTION

WORD-LEVEL ANALYSIS

LETTER-TO-SOUND RULES

MORPHOPHONEMICS AND LEXICAL STRESS

ORTHOGRAPHIC CONVENTIONS

PART-OF-SPEECH ASSIGNMENT

PARSING

PROSODIC MARKING

DISCOURSE-LEVEL EFFECTS

THE FUTURE

SPEECH RECOGNITION TECHNOLOGY

Speech Recognition Technology: A Critique

State of the Art in Continuous Speech Recognition

THE SPEECH RECOGNITION PROBLEM

General Synthesis/Recognition Process.

Units of Speech

HIDDEN MARKOV MODELS

Markov Chains

Hidden Markov Models

Phonetic HMMs

A HISTORICAL OVERVIEW

TRAINING AND RECOGNITION

Feature Extraction

Training

Phonetic HMMs and Lexicon

Grammar

Recognition

STATE OF THE ART

Improvements in Performance

Common Speech Corpora

Acoustic Modeling

Language Modeling

Research Experimentation Cycle

Sample Performance Figures

Effects of Training and Grammar

Speaker-Dependent vs. Speaker-Independent Recognition

Adaptation

Adding New Words

REAL-TIME SPEECH RECOGNITION

ALTERNATIVE MODELS

Segmental Models

Neural Networks

Training and Search Methods for Speech Recognition

ESTIMATION OF STATISTICAL PARAMETERS OF HMMS

REMARKS ON THE ESTIMATION PROCEDURE

FINDING THE MOST LIKELY PATH

DECODING: FINDING THE MOST LIKELY WORD SEQUENCE

NATURAL LANGUAGE UNDERSTANDING TECHNOLOGY

The Roles of Language Processing in a Spoken Language Interface

Background: The ARPA Spoken Language Program

THE DUAL ROLE OF LANGUAGE PROCESSING

Approaches to Spoken Language Understanding

Interfacing Speech and Language

Progress in Spoken Language Understanding

THE ROLE OF DISCOURSE

Constraints on Reference

Constraints from Mixed Initiative

Order in Problem Solving and Dialogue

Discourse Constraints in a Spoken Language System

EVALUATION

CONCLUSIONS

Models of Natural Language Understanding

A BRIEF HISTORY OF NLP

WHY IS NLP DIFFICULT?

WHAT IS IN AN NLP SYSTEM?

Syntax

Semantics

Discourse and Pragmatics

Reasoning, Response Planning, and Response Generation

Simplifying the Problem

Another View

HOW CAN NL SYSTEMS BE APPLIED AND EVALUATED?.

CONCLUSIONS

Integration of Speech with Natural Language Understanding

COPING WITH SPONTANEOUS SPOKEN LANGUAGE

Language Phenomena in Spontaneous Speech

Strategies for Handling Spontaneous Speech Phenomena

ROBUSTNESS TO RECOGNITION ERRORS

NATURAL LANGUAGE CONSTRAINTS IN RECOGNITION

Models for Integration

Architectures for Integration

Word Lattice Parsing

Dynamic Grammar Networks

N-best Filtering or Rescoring

Integration Results

SPEECH CONSTRAINTS IN NATURAL LANGUAGE UNDERSTANDING

APPLICATIONS OF VOICE-PROCESSING TECHNOLOGY I

A Perspective on Early Commerical Applications of Voice-Processing Technology for Telecommunicationsand Aids for the…

CURRENT COMMERCIAL APPLICATIONS: TELEPHONE BASED

CURRENT COMMERCIAL APPLICATIONS: AIDS TO THE HANDICAPPED

Applications of Voice-Processing Technology in Telecommunications

THE VISION

THE ART OF SPEECH RECOGNITION AND SYNTHESIS

APPLICATIONS OF SPEECH RECOGNITION AND SYNTHESIS

SPEECH TECHNOLOGY TELECOMMUNICATIONS MARKET

Cost Reduction vs. New Revenue Opportunities

Automation of Operator Services

Voice Access to Information over the Telephone Network

Voice Dialing

Voice-Interactive Phone Service

Directory Assistance Call Completion

Reverse Directory Assistance

Telephone Relay Service

FUTURE POSSIBILITIES

Near-Term Technical Challenges

Personal Communication Networks and Services

Predictions

Speech Processing for Physical and Sensory Disabilities

ASSISTIVE HEARING TECHNOLOGY

Background

Hearing Aids and Assistive Listening Devices

Visual Sensory Aids

Tactile Sensory Aids.

Direct Electrical Stimulation of the Auditory System

Noise Reduction

OTHER FORMS OF ASSISTIVE TECHNOLOGY INVOLVING VOICE COMMUNICATION

Speech Processing for Sightless People

Augmentative and Alternative Communication

Assistive Voice Control: Miscellaneous Applications

ACKNOWLEDGMENT

APPLICATIONS OF VOICE-PROCESSING TECHNOLOGY II

Commercial Applications of Speech Interface Technology: An Industry at the Threshold

BACKGROUND

TECHNOLOGY

THE ADVANCED SPEECH TECHNOLOGY MARKET

RECENT MARKET TRENDS

MARKET SIZE

RECENT SIGNIFICANT COMMERCIAL DEVELOPMENTS

FUTURE APPLICATIONS

Military and Government Applications of Human-Machine Communication by Voice

TECHNOLOGY TRENDS AND NEEDS

SUMMARY OF VISITS AND CONTACTS

ARMY APPLICATIONS

NAVY APPLICATIONS

AIR FORCE APPLICATIONS

AIR TRAFFIC CONTROL APPLICATIONS

LAW ENFORCEMENT APPLICATIONS

SUMMARY OF USERS AND APPLICATIONS

TECHNOLOGY TRANSFER

TECHNOLOGY DEPLOYMENT

Deployment of Human-Machine Dialogue Systems

DEGREE OF DIFFICULTY OF A VOICE DIALOGUE APPLICATION

Dimensions of the Speech Recognition Task

Dimensions of the Language-Understanding Task

Dimensions of the Speech Synthesis Task

Additional Dimensions of Difficulty

Examples of Speech Applications

PROCEDURE FOR DEPLOYMENT OF SPEECH APPLICATIONS

The Art of Human-Machine Dialogues

What Does Voice-Processing Technology Support Today?

SYSTEM TECHNOLOGIES

Hardware Technology

Microprocessors

Digital Signal Processors

Equipment and Systems

Application Technology Trend

Development Environment for DSP

Application Development Environment.

Speech Input/Output Operating Systems.

Notes:

Based on a colloquium sponsored by the National Academy of Sciences.

Includes bibliographical references and index.

ISBN:

9786610195909

9781280195907

1280195908

9780309556255

0309556252

9780585001814

0585001812

OCLC:

923267327