• Journal of the Korea Computer Industry Society
• /
• v.2 no.2
• /
• pp.195-202
• /
• 2001

In this paper, we show a study on how to model a phoneme of which acoustic feature is changed according to both left-hand and right-hand phonemes. For this purpose, we make a comparative study on two kinds of algorithms; a unit reduction algorithm and decision tree modeling. The unit reduction algorithm uses only statistical information while the decision tree modeling uses statistical information and Korean acoustical information simultaneously. Especially, we focus on how to model context-dependent phonemes based on decision tree modeling. Finally, we show the recognition rate when context-dependent phonemes are obtained by the decision tree modeling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.224-229
• /
• 1999

In the field of speech recognition, the research area can be classified into the following two categories: one which is concerned with the development of phoneme-level recognition system, the other with the efficiency of word-level recognition system. The resonable phoneme-level recognition system should detect the phonemic boundaries appropriately and have the improved recognition abilities all the more. The traditional LPC methods detect the phoneme boundaries using Itakura-Saito method which measures the distance between LPC of the standard phoneme data and that of the target speech frame. The MFCC methods which treat spectral transitions as the phonemic boundaries show the lack of adaptability. In this paper, we present new speech recognition system which uses auto-correlation method in the phonemic boundary detection process and the multi-layered Feed-Forward neural network in the recognition process respectively. The proposed system outperforms the traditional methods in the sense of adaptability and another advantage of the proposed system is that feature-extraction part is independent of the recognition process. The results show that frame-unit phonemic recognition system should be possibly implemented.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1991.06a
• /
• pp.58-63
• /
• 1991

This paper describes development of small scale voice dialing system using TMS320C30. Recognition vocabuliary is used 50 department name within university. In vocabulary below the middle scale, word unit recognition is more practice than phoneme unit or syllable unit recognition. In this paper, we performend recognition and model generation using DMS(Dynamic Multi-Section) and implemeted voice dialing system using TMS320C30. As a result of recognition, we achieved a 98% recognition rate in condition of section 22 and weight 0.6 and recognition time took 4 seconds.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.1
• /
• pp.4-10
• /
• 2000

The work presented in this paper is about a postprocessor, which improves the performance of automatic speech segmentation system by correcting the phoneme boundary errors. We propose a postprocessor that reduces the range of errors in the auto labeled results that are ready to be used directly as synthesis unit. Starting from a baseline automatic segmentation system, our proposed postprocessor trains the features of hand labeled results using multi-layer perceptron(MLP) algorithm. Then, the auto labeled result combined with MLP postprocessor determines the new phoneme boundary. The details are as following. First, we select the feature sets of speech, based on the acoustic phonetic knowledge. And then we have adopted the MLP as pattern classifier because of its excellent nonlinear discrimination capability. Moreover, it is easy for MLP to reflect fully the various types of acoustic features appearing at the phoneme boundaries within a short time. At the last procedure, an appropriate feature set analyzed about each phonetic event is applied to our proposed postprocessor to compensate the phoneme boundary error. For phonetically rich sentences data, we have achieved 19.9 % improvement for the frame accuracy, comparing with the performance of plain automatic labeling system. Also, we could reduce the absolute error rate about 28.6%.

• Journal of Digital Convergence
• /
• v.11 no.10
• /
• pp.367-372
• /
• 2013

In Speech recognition system, there is a problem with phoneme in the model training and it cause a stored mode regeneration process which come into being appear time and more costs. In this paper, we propose the methode of likely phoneme model schema using decision tree clustering. Proposed system has a robust and correct sound model which system apply the decision tree clustering methode form generate model, therefore this system reduce the regeneration process and provide a retrieve the phoneme unit in probability model. Also, this proposed system provide a additional likely phoneme model and configured robust correct sound model. System performance as a result of represent vocabulary dependence recognition rate of 98.3%, vocabulary independence recognition rate of 98.4%.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.665-672
• /
• 2003

This paper describes a speech synthesis technique by concatenating unit phoneme. At that time, a major problem is that discontinuity is happened from connection part between unit phonemes, especially from connection part between unit phonemes recorded by different persons. To solve the problem, this paper uses clustered diphone, and proposes a spectral smoothing technique, not only using formant trajectory and distribution characteristic of spectrum but also reflecting human's acoustic characteristic. That is, the proposed technique performs unit phoneme clustering using distribution characteristic of spectrum at connection part between unit phonemes and decides a quantity and a scope for the smoothing by considering human's acoustic characteristic at the connection part of unit phonemes, and then performs the spectral smoothing using weights calculated along a time axes at the border of two diphones. The proposed technique removes the discontinuity and minimizes the distortion which can be occurred by spectrum smoothing. For the purpose of the performance evaluation, we test on five hundred diphones which are extracted from twenty sentences recorded by five persons, and show the experimental results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.2
• /
• pp.40-45
• /
• 2003

This is the study on recognition units and segmentation of phonemes. In the case of making large vocabulary speech recognition system, it is better to use the segment than the syllable or the word as the recognition unit. In this paper, we study on the proper recognition units and segmentation of phonemes for Korean speech recognition. For experiments, we use the speech toolkit of OGI in U.S.A. The result shows that the recognition rate of the case in which the diphthong is established as a single unit is superior to that of the case in which the diphthong is established as two units, i.e. a glide plus a vowel. And recognizer using manually-aligned training data is a little superior to that using automatically-aligned training data. Also, the recognition rate of the case in which the bipbone is used as the recognition unit is better than that of the case in which the mono-Phoneme is used.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.6-9
• /
• 2003

In this paper, we studied on the difference of speaker adaptation according to the phoneme classification for Korean Speech recognition. In order to study of speech adaptation according to the weight of difference of phoneme as recognition unit, we used SCHMM as recognition system. And Speaker adaptation method used in this paper was MAPE(Maximum A Posteriori Probability Estimation), Linear Spectral Estimation. In order to evaluate the performance of these methods, we used 10 Korean isolated numbers as the experimental data. It is possible for the first and the second methods to be carried out unsupervised learning and used in on-line system. And the first method was shown performance improvement over the second method, and hybrid adaptation showed the better recognition results than those which performed each method. And the result of Speaker adaptation using the variable weight according to the phoneme had better than the result using fixed weight.

• Speech Sciences
• /
• v.11 no.3
• /
• pp.23-36
• /
• 2004

Many languages show reverse durational variation between preceding vowel and following voiced/voiceless (lax/tense) consonants. This study investigated the likely effects of phoneme type (tense vs. lax) on the timing structure (duration of syllable, word, phrase and sentence) of Korean. Three rates of speech (fast, normal, slow) applied to stimuli with the target word /a-Ca/ where /C/ is one of /p, p', $p^h$/. The type (tense/lax) of /C/ caused marked inverse durational variations in the two syllables /a/ and /Ca/ and highly different durational ratios between them. Words with /p', $p^h$/ were significantly longer than that with /p/, which contrasts with many other languages where such pairs of words have a similar duration. The differentials between words remained up to the phrase and sentence level, but in general the higher linguistic units did not statistically differ within each level. Thus, the phrase is suggested as a compensatory unit of phoneme type effects in Korean. Different rates did not affect the general tendency. Distribution of time variations (from normal to fast and slow) to each syllable (/a/ and /Ca/) was also observed.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.175-179
• /
• 2003

In order to produce a high quality (intelligibility and naturalness) synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model. In this paper, we analyzed Chinese texts using a segmentation, POS tagging and unknown word recognition. We present a grapheme-to-phoneme conversion using a dictionary-based and rule-based method. We constructed a prosody model using a probabilistic method and a decision tree-based error correction method. According to the result from the above analysis, we can successfully select and concatenate exact synthesis unit of syllables from the Chinese Synthesis DB.