Skip to main content
SpringerLink
Log in

Automatic Speech Recognition

The Development of the SPHINX System

  • Book
  • © 1989

Overview

Authors:
  1. Kai-Fu Lee

    1. Carnegie Mellon University, Pittsburgh, USA

    View author publications

    You can also search for this author in PubMed   Google Scholar

This is a preview of subscription content, log in via an institution to check access.

Access this book

Log in via an institution
eBook USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (9 chapters)

  1. Front Matter

    Pages i-xv
    Download chapter PDF

  2. Introduction

    • Kai-Fu Lee
    Pages 1-16

  3. Hidden Markov Modeling of Speech

    • Kai-Fu Lee
    Pages 17-43

  4. Task and Databases

    • Kai-Fu Lee
    Pages 45-50

  5. The Baseline SPHINX System

    • Kai-Fu Lee
    Pages 51-62

  6. Adding Knowledge

    • Kai-Fu Lee
    Pages 63-89

  7. Finding a Good Unit of Speech

    • Kai-Fu Lee
    Pages 91-114

  8. Learning and Adaptation

    • Kai-Fu Lee
    Pages 115-127

  9. Summary of Results

    • Kai-Fu Lee
    Pages 129-136

  10. Conclusion

    • Kai-Fu Lee
    Pages 137-144

  11. Back Matter

    Pages 145-207
    Download chapter PDF
Back to top

Keywords

About this book

Speech Recognition has a long history of being one of the difficult problems in Artificial Intelligence and Computer Science. As one goes from problem solving tasks such as puzzles and chess to perceptual tasks such as speech and vision, the problem characteristics change dramatically: knowledge poor to knowledge rich; low data rates to high data rates; slow response time (minutes to hours) to instantaneous response time. These characteristics taken together increase the computational complexity of the problem by several orders of magnitude. Further, speech provides a challenging task domain which embodies many of the requirements of intelligent behavior: operate in real time; exploit vast amounts of knowledge, tolerate errorful, unexpected unknown input; use symbols and abstractions; communicate in natural language and learn from the environment. Voice input to computers offers a number of advantages. It provides a natural, fast, hands free, eyes free, location free input medium. However, there are many as yet unsolved problems that prevent routine use of speech as an input device by non-experts. These include cost, real time response, speaker independence, robustness to variations such as noise, microphone, speech rate and loudness, and the ability to handle non-grammatical speech. Satisfactory solutions to each of these problems can be expected within the next decade. Recognition of unrestricted spontaneous continuous speech appears unsolvable at present. However, by the addition of simple constraints, such as clarification dialog to resolve ambiguity, we believe it will be possible to develop systems capable of accepting very large vocabulary continuous speechdictation.

Authors and Affiliations

  • Carnegie Mellon University, Pittsburgh, USA

    Kai-Fu Lee

Bibliographic Information

Publish with us

Policies and ethics

Back to top

Search

Navigation