This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition. First, a general principle of time-normalization is given using time-warping function. Then, two time-normalized distance definitions, called symmetric and asymmetric forms, are derived from the principle. These two forms are compared with each other through theoretical discussions and experimental studies. 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. The effective slope constraint characteristic is qualitatively analyzed, and the optimum slope constraint condition is determined through experiments. The optimized algorithm is then extensively subjected to experimental comparison with various DP-algorithms, previously applied to spoken word recognition by different research groups. The experiment shows that the present algorithm gives no more than about two-thirds errors, even compared to the best conventional algorithm.

Dynamic programming algorithm optimization for spoken word recognition

Several parametric representations of the acoustic signal were compared with regard to word recognition performance in a syllable-oriented continuous speech recognition system. The vocabulary included many phonetically similar monosyllabic words, therefore the emphasis was on the ability to retain phonetically significant acoustic information in the face of syntactic and duration variations. For each parameter set (based on a mel-frequency cepstrum, a linear frequency cepstrum, a linear prediction cepstrum, a linear prediction spectrum, or a set of reflection coefficients), word templates were generated using an efficient dynamic warping method, and test data were time registered with the templates. A set of ten mel-frequency cepstrum coefficients computed every 6.4 ms resulted in the best performance, namely 96.5 percent and 95.0 percent recognition with each of two speakers. The superior performance of the mel-frequency cepstrum coefficients may be attributed to the fact that they better represent the perceptually relevant aspects of the short-term speech spectrum.

Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences

This paper provides a review of recent developments in speech recognition research. The concept of sources of knowledge is introduced and the use of knowledge to generate and verify hypotheses is discussed. The difficulties that arise in the construction of different types of speech recognition systems are discussed and the structure and performance of several such systems is presented. Aspects of component subsystems at the acoustic, phonetic, syntactic, and semantic levels are presented. System organizations that are required for effective interaction and use of various component subsystems in the presence of error and ambiguity are discussed.

Speech recognition by machine: A review

Approximate matching of strings is reviewed with the aim of surveying techniques suitable for finding an item in a database when there may be a spelling mistake or other error in the keyword. The methods found are classified as either equivalence or similarity problems. Equivalence problems are seen to be readily solved using canonical forms. For sinuiarity problems difference measures are surveyed, with a full description of the wellestablmhed dynamic programming method relating this to the approach using probabilities and likelihoods. Searches for approximate matches in large sets using a difference function are seen to be an open problem still, though several promising ideas have been suggested. Approximate matching (error correction) during parsing is briefly reviewed.

http://www.quretec.com/u/vilo/edu/2002-03/Tekstialgoritmid_I/Articles/Approximate/Hall_Dowling_Approximate_Matching_Review_1980_p381-hall.pdf

Approximate String Matching

The technique of dynamic programming for the time registration of a reference and a test pattern has found widespread use in the area of isolated word recognition. Recently, a number of variations on the basic time warping algorithm have been proposed by Sakoe and Chiba, and Rabiner, Rosenberg, and Levinson. These algorithms all assume that the test input is the time pattern of a feature vector from an isolated word whose endpoints are known (at least approximately). The major differences in the methods are the global path constraints (i.e., the region of possible warping paths), the local continuity constraints on the path, and the distance weighting and normalization used to give the overall minimum distance. The purpose of this investigation is to study the effects of such variations on the performance of different dynamic time warping algorithms for a realistic speech database. The performance measures that were used include: speed of operation, memory requirements, and recognition accuracy. The results show that both axis orientation and relative length of the reference and the test patterns are important factors in recognition accuracy. Our 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. Results with this new algorithm show performance comparable to or better than that of all other dynamic time warping algorithms that were studied.

/pdf/performance-tradeoffs-in-dynamic-time-warping-algorithms-for-52yqx6n88g.pdf

Performance tradeoffs in dynamic time warping algorithms for isolated word recognition

Automatic speech recognition experiments are described in which several popular preprocessing and classification strategies are compared. Preprocessing is done either by linear predictive analysis or by bandpass filtering. The two approaches are shown to produce similar recognition scores. The classifier uses either linear time stretching or dynamic programming to achieve time alignment. It is shown that dynamic programming is of major importance for recognition of polysyllabic words. The speech is compressed into a quasi-phoneme character string or preserved uncompressed. Best results are obtained with uncompressed data, using nonlinear time registration for multisyllabic words.

G. White

Papers

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