Dynamic programming algorithm optimization for spoken word recognition

  title={Dynamic programming algorithm optimization for spoken word recognition},
  author={Hiroaki Sakoe and Seibi Chiba},
  journal={IEEE Transactions on Acoustics, Speech, and Signal Processing},
  • H. SakoeS. Chiba
  • Published 1 February 1978
  • Computer Science
  • IEEE Transactions on Acoustics, Speech, and Signal Processing
This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition. [] Key Method The symmetric form algorithm superiority is established. A new technique, called slope constraint, is successfully introduced, in which the warping function slope is restricted so as to improve discrimination between words in different categories.

Figures and Tables from this paper

Performance tradeoffs in dynamic time warping algorithms for isolated word recognition

The results suggest a new approach to dynamic time warping for isolated words in which both the reference and test patterns are linearly warped to a fixed length, and then a simplified dynamic time Warping algorithm is used to handle the nonlinear component of the time alignment.

Genetic algorithm for optimizing the nonlinear time alignment of automatic speech recognition systems

A stochastic method called the genetic algorithm (GA), which is used to solve the nonlinear time alignment problem, is presented and experimental results show that the GA has a better performance than the DTW.

On time alignment and metric algorithms for speech recognition

An algorithm for comparing speech waveforms to decide if the spoken utterance is part of a given vocabulary of word waveforms or not, and if it is part the vocabulary, to choose the matching word is presented and preliminary results show that the algorithm provides high probability of correct classification.

The use of a one-stage dynamic programming algorithm for connected word recognition

The algorithm to be developed is essentially identical to one presented by Vintsyuk and later by Bridle and Brown, but the notation and the presentation have been clarified and the computational expenditure per word is independent of the number of words in the input string.

Improvements in isolated word recognition

Possibility for improving the recognition accuracy are investigated for a given feature extraction, which is based on a short term spectrum analysis by means of band-pass filtering and a method based on spectral change is investigated, alone and in combination with dynamic programming.

Spoken-word recognition using dynamic features analysed by two-dimensional cepstrum

Using word and monosyllable recognition experiments based on dynamic programming (DP) matching of a time sequence of the TDC, it is confirmed that the global static features (spectral envelope) and global dynamic features are both effective for speech recognition.

The Nonlinear Time Alignment Model for Speech Recognition System

The new nonlinear time alignment model, which is much faster than widely accepted DTW algorithms, is presented, which shows comparable or better recognition efficiency and is robust to end point variations.

Locally constrained dynamic programming in automatic speech recognition

A technique for obtaining an estimate of local timescale variability based on a bi-directional dynamic programming algorithm and basic fuzzy set theory is described and results indicate that this technique will lead to improved discrimination, especially if the differences between classes are mainly due to temporal structure.

Speaker-independent word recognition using dynamic programming matching with statistic time warping cost

  • Takao Watanabe
  • Computer Science
    ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing
  • 1988
A speaker-independent word recognition method is presented to improve word recognition performance without using a large training pattern set. The method is based on a multiple-template technique for

Considerations in dynamic time warping algorithms for discrete word recognition

An algorithm in which an uncertainty exists in the registration both for initial and final frames was studied and another which constrains the dynamic path to follow the path which is locally minimum at each frame.



Minimum prediction residual principle applied to speech recognition

A computer system is described in which isolated words, spoken by a designated talker, are recognized through calculation of a minimum prediction residual through optimally registering the reference LPC onto the input autocorrelation coefficients using the dynamic programming algorithm.

Speech recognition experiments with linear predication, bandpass filtering, and dynamic programming

Automatic speech recognition experiments are described in which several popular preprocessing and classification strategies are compared and it is shown that dynamic programming is of major importance for recognition of polysyllabic words.

Automatic recognition of 200 words

Comparative study of DP-pattern matching techniques for speech recognition

  • Group Meeting Speech, Acoust. SOC. Japan, Preprints

Applied Dynamic Programming

Real-time speech recognition system by minicomputer with DP processor

  • I 9 74 Tech. Group Meeting Speech

Nat. Meeting, Inst. Electron. Comm. Eng. Japan

  • Nat. Meeting, Inst. Electron. Comm. Eng. Japan
  • 1970

A similarity evaluation of speech patterns by dynamic programming ” ( in Japanese ) , presented at the Dig