Wyniki wyszukiwania - BazTech

1

Phoneme Segmentation Based on Wavelet Spectra Analysis

Ziółko B., Manandhar S., Wilson R. C., Ziółko M.

Archives of Acoustics

|

2011

|

Vol. 36, No. 1

29-47

EN

A phoneme segmentation method based on the analysis of discrete wavelet transform spectra is described. The localization of phoneme boundaries is particularly useful in speech recognition. It enables one to use more accurate acoustic models since the length of phonemes provide more information for parametrization. Our method relies on the values of power envelopes and their first derivatives for six frequency subbands. Specific scenarios that are typical for phoneme boundaries are searched for. Discrete times with such events are noted and graded using a distribution-like event function, which represent the change of the energy distribution in the frequency domain. The exact definition of this method is described in the paper. The final decision on localization of boundaries is taken by analysis of the event function. Boundaries are, therefore, extracted using information from all subbands. The method was developed on a small set of Polish hand segmented words and tested on another large corpus containing 16 425 utterances. A recall and precision measure specifically designed to measure the quality of speech segmentation was adapted by using fuzzy sets. From this, results with F-score equal to 72.49% were obtained.

2

Rule Based Speech Signal Segmentation

Greibus M., Telksnys L.

Journal of Telecommunications and Information Technology

|

2010

|

nr 4

37-43

EN

This paper presents the automated speech signal segmentation problem. Segmentation algorithms based on energetic threshold showed good results only in noise-free environments. With higher noise level automatic threshold calculation becomes complicated task. Rule based postprocessing of segments can give more stable results. Off-line, on-line and extrema types of rules are reviewed. An extrema-type segmentation algorithm is proposed. This algorithm is enhanced by a rule base to extract higher energy level segments from noise. This algorithm can work well with energy like features. The experiments were made to compare threshold and rule-based segmentation in different noise types. Also was tested if multifeature segmentation can improve segmentation results. The extrema rule-based segmentation showed smaller error ratio in different noise types and levels. Proposed algorithm does not require high calculation resources. Such algorithm can be processed by devices with limited computing power.

3

Segmentacja mowy polskiej z wykorzystaniem transformacji falkowej

Tarasiuk M., Gosiewski Z.

Acta Mechanica et Automatica

|

2010

|

Vol. 4, no. 1

92-95

PL

W artykule przedstawiono koncepcję metody segmentacji słów wypowiadanych w języku polskim. Jako narzędzie w procesie segmentacji wykorzystano transformację falkową. Zaproponowano algorytm postępowania oraz przedstawiono wyniki prowadzonych prac badawczych. Wykorzystując opracowaną metodę dokonano podziału wypowiadanych słów i sprawdzono poprawność jego wykonania. Niniejsze badanie stanowi platformę bazową do dalszych prac zmierzających w kierunku opracowania automatycznego systemu rozpoznawania mowy. Badania i obliczenia wykonywano w oparciu o oprogramowanie Matlab.

EN

This article introduces an conception on polish spoken words segmentation using wavelet transformation. There was suggested an algorithm and presented achievements made during researches. Spoken words were then divided and their segmentation correctness was verified with use of mentioned above method. This study provides a base platform for further development of the automatic speech recognition system. Research and calculations were executed in MATLAB.

4

Dynamic programming method for fine-tuning the boundary points in automatic segmentation of speech

Szymański M., Grocholewski S.

Archives of Acoustics

|

2007

|

Vol. 32, No. 1

127-134

EN

The important element of today's speech systems is the set of recorded wavefiles annotated by a sequence of phonemes and boundary time-points. As the manual segmentation of speech is a very laborious task, there is the need for automatic segmentation algorithms. However, it was observed that common HMM-based methods are prone to systematical errors. Thus, some boundary refinement approaches were introduced. In this paper we combine two sources of information: boundary error distribution and an acoustic observation distribution, in a single dynamic programming approach.

5

Transcription-based automatic segmentation of speech

Szymański M., Grocholewski S.

Archives of Control Sciences

|

2005

|

Vol. 15, no. 3

461--468

EN

The important element of today's speech systems is the set of recorded wavefiles annotated by a sequence of phonemes and boundary time-points. The manual segmentation of speech is a very laborious task, hence the need for automatic segmenation algorithms. However, the manual segmentation still outperforms the automatic one and at the same time the quality of resulting synthetic voice highly depends on the accuracy of the phonetic segmentation. This paper describes our methodology and implementation of automatic speech segmentation, emphasizing its new elements.