Whither speech recognition?

@article{Samuel1969WhitherSR,
  title={Whither speech recognition?},
  author={Arthur L. Samuel and J. R. Pierce},
  journal={The Journal of the Acoustical Society of America},
  year={1969},
  volume={47 6},
  pages={
          1616-7
        }
}
  • A. SamuelJ. Pierce
  • Published 1 October 1969
  • Psychology
  • The Journal of the Acoustical Society of America
Speech recognition has glamour. Funds have been available. Results have been less glamorous. “When we listen to a person speaking much of what we think we hear is supplied from our memory. [W. James, Talks to Teachers on Psychology and to Students on Some of Life's Ideals (Holt, New York, 1889), p. 159]. General‐purpose speech recognition seems far away Special‐purpose speech recognition is severely limited. It would seem appropriate for people to ask themselves why they are working in the… 

Speech Recognition and Understanding

This chapter describes the techniques developed and the progress made in speech recognition and understanding in the early 1970’s.

CAN AUTOMATIC SPEECH RECOGNITION LEARN MORE FROM HUMAN SPEECH PERCEPTION ?

Although the mechanisms of human speech perception are not fully understood, some findings from neuroscience, physiology, cognitive science and psychology could potentially lead to new understanding and thereby stimulate the development of new techniques and architectures for automatic speech recognition that will bridge and reduce the performance gap between machines and humans.

Working Papers in Speech Recognition - I,

Abstract : The report is a collection of Working Papers in Speech Recognition on the following topics: Organization of the HEARSAY II speech understanding system; The DRAGON system -- an overview;

Opportunities for re-convergence of engineering and cognitive science accounts of spoken word recognition

The relationship between the engineering and cognitive science communities within the relatively well-defined sub-field of spoken word recognition is explored and some elements of a joint research programme are proposed which could act as a stimulus for the two communities to work together.

Evaluating speech recognizers

A standard for comparing the performance of different recognizers on arbitrary vocabularies based on a human word recognition model is developed, which allows recognition results to be normalized for comparison according to two intuitively meaningful figures of merit.

Whither speech recognition: the next 25 years

The dimensions of the speech recognition task, speech feature analysis, pattern classification using hidden Markov models, language processing, and the current accuracy of speech recognition systems are discussed.

Eyes and Ears for Computers

This paper represents a comparitive study of the issues, systems and unsolved problems that are, at present, of interest to visual and speech recognition research.

Perceptual Properties of Current Speech Recognition Technology

It is argued that the engineering techniques for automatic recognition of speech that are already in widespread use are often consistent with some well-known properties of the human auditory system.

Speech Pattern Processing

The study of ‘speech’ is a fragmented multi-disciplinary area of science which sits somewhere between acoustics, linguistics, engineering and psychology. The one unifying force, which links all of
...

Some experiments in spoken word recognition

Experimental work in the recognition of limited-size, but arbitrary, vocabularies of spoken words using a filter-bank voice-spectrum analyzer providing real-time input of measurement data to an IBM 1620-II digital computer system.

Speech Analysis, Synthesis and Perception

A second edition was begun in 1970, the aim was to retain the original format, but to expand the content, especially in the areas of digital communications and com puter techniques for speech signal processing.

Results Obtained from a Vowel Recognition Computer Program

As a first step toward a general speech recognition computer program, a program has been developed to recognize ten Eng.ish vowels in isolated words of the form /b/—bowel—/t/. Input to the computer

A method of analysis and recognition for voiced vowels

A method of speech analysis that has been shown to be capable of recognizing with high accuracy a set of seven voiced vowels spoken by twelve male talkers with various regional accents is described, indicating a linear separabilitly of the vowel sounds in the space described by the correlation operations.

SPEECH RECOGNITION BY FEATURE-ABSTRACTION TECHNIQUES.

Abstract : A speech-analysis system using analog-threshold logic (ATL) for feature abstraction has been developed to recognize consonants in utterances of CVC words by a number of talkers. The

Spoken Digit Recognition Using Vowel‐Consonant Segmentation

A procedure has been developed for recognition of spoken digits by means of digital computer simulation. Using power spectra computed at 10‐msec intervals, the words are segmented into vowels and

Spoken Digit Recognition Using Time‐Frequency Pattern Matching

A study of the machine recognition of the spoken digits zero through nine has been carried out by a digital computer simulation. The spoken utterances are converted to time‐frequency patterns of

VOICE TO TELETYPE CODE CONVERTER RESEARCH PROGRAM. PART II. EXPERIMENTAL VERIFICATION OF A METHOD TO RECOGNIZE PHONETIC SOUNDS

The consonant recognition program provided completely automatic location and recognition of the initial consonants with a mean accuracy of 60% for ten male talkers speaking isolated CVC words made up of all combinations of these initial consonant, ten vowels, and the final consonant d.

APPLICATION OF ADAPTIVE THRESHOLD ELEMENTS TO THE RECOGNITION OF ACOUSTIC-PHONETIC STATES.

  • J. E. Dammann
  • Computer Science
    The Journal of the Acoustical Society of America
  • 1965
It was shown that the selection of an output code can significantly affect the generalization and that sequences of recognized samples can represent dynamic changes through words.

Electronic Binary Selection System for Phoneme Classification

A successive binary‐selection system for automatic classification of spoken English into several groups of phonemes is described. The first step separates voiced from unvoiced by measuring the