• The Journal of the Acoustical Society of Korea
• /
• v.17 no.7
• /
• pp.22-27
• /
• 1998

본 논문에서는 ETRI에서 개발한 가변 어휘 음성 인식기의 어휘 독립 음향 모델링 방법을 기술하고, 이 모델의 어휘 종속, 어휘 독립 및 어휘적응 성능을 평가하기 위하여 다 양한 고립단어 및 연속음성 DB에 대하여 실험한 결과를 분석하였다. 평가를 위하여 사용한 음성 DB로는 고립단어 음성으로 POW(Phonetically Optimized Words) 3848, PBW(Phonetically Balanced Words) 445, PBW 452, 호텔예약 244 단어, 게임 제어용 단어 등이며, 연속음성으로 일반 문장 음성 및 연속 숫자음을 이용하였다. 성능 분석 결과 40개 음소 모델만으로도 비교적 높은 인식률을 보여 주었지만, 어휘독립의 경우는 어휘종속에 비 하여 성능이 크게 낮았고, 특히 대상 어휘가 숫자음, 알파벳, 연속음 등의 경우에는 POW 데이터나 PBW 데이터만 가지고는 우수한 가변 어휘 음성 인식기를 구현하기에 한계가 있 음을 알 수 있다. 또한, 훈련 데이터의 어휘와 평가데이터의 어휘가 비슷할 경우에는 변이음 모델을 사용하면 음소 모델만을 사용할 경우에 비하여 그 성능이 우수하였지만, 일반적인 어휘독립의 상황에서는 효과가 별로 없음을 알 수 있었다.

• Journal of the Society of Naval Architects of Korea
• /
• v.54 no.2
• /
• pp.125-131
• /
• 2017

In order to develop test and performance analysis techniques for a CRP propulsion, a CRP dynamometer which can be installed inside the model ship was designed and manufactured. The object ship was the 16000TEU container carrier, which has test results for the single propeller. The design concept of the present CRP is that forward & after propellers have the same power ratio and their RPM ratio is 0.75:1. To begin with, we checked the performance of the CRP dynamometer through the calibration and then installed it inside the model ship. After the model ship setup including the design CRP and the rudder in the Large Cavitation Tunnel(LCT), a series of model tests composed of power ratio check, propeller behind wake(PBW) test, cavitation observation and pressure fluctuation tests was conducted. Through the model test and data analysis for CRP, the experimental technique was established and the improved method for CRP design was suggested.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.383-389
• /
• 2004

In this paper. we propose the bias compensation methods and the eigenvoice method using the mean of dimensional eigenvoice to improve the performance of rapid speaker adaptation based on eigenvoice under mismatch between training and test environment. Experimental results for vocabulary-independent word recognition task (using PBW 452 DB) show that the proposed methods yield improvements for small adaptation data. We obtained about 22∼30% relative improvement by the bias compensation methods as amount of adaptation data varied from 1 to 50, and obtained 41% relative improvement in error rate by the eigenvoice method using the mean of dimensional eigenvoice with only single adaptation word.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.663-667
• /
• 1999

In this paper, we review the conventional speaker verification algorithm and present the text-dependent speaker verification system for application over telephone lines and its result of experiments. We apply blind-segmentation algorithm which segments speech into sub-word unit without linguistic information to the speaker verification system for training speaker model effectively with limited enrollment data. And the World-mode] that is created from PBW DB for score normalization is used. The experiments are presented in implemented system using database, which were constructed to simulate field test, and are shown 3.3% EER.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.651-660
• /
• 2019

The present study aims to find out the necessary speech sound level which can satisfy with the speech intelligibility in a noisy classroom environments. For this, auralized materials were made to undertake listening tests with 27 people. Speech intelligibility tests were carried out using both Consonant-Vowel-Consonant (CVC) and Phonetically Balanced Words (PBW) methods. Signal to noise ratio was changed by 5 dB for each test. As a result, it was found that speech intelligibilities are increasing with larger Signal to Noise Ratio (SNR). It was also found that there is a lot of difference of speech intelligibilities by SNR for syllables (CVC) with the Reverberation Time (RT) of 1.5 s. However, any significant difference was not found for words (PBW) in the case with RTs of below 0.8 s. Also, it was revealed through the 2-way analysis of variance (ANOVA) test that SNR is the only attentive factor which can affect the Korean speech intelligibilities for both PBW and CVC methods. Therefore, RTs below 0.8 s could be the acoustic criteria for classroom which can minimize the effects of noise. In the case with RTs larger than 0.8 s, much larger SNR is needed to give sufficient speech intelligibility.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.259-266
• /
• 2014

In this paper, we propose a novel technique for noise robust automatic speech recognition (ASR). The development of ASR techniques has made it possible to recognize isolated words with a near perfect word recognition rate. However, in a highly noisy environment, a distinct mismatch between the trained speech and the test data results in a significantly degraded word recognition rate (WRA). Unlike conventional ASR systems employing Mel-frequency cepstral coefficients (MFCCs) and a hidden Markov model (HMM), this study employ histogram of oriented gradient (HOG) features and a Support Vector Machine (SVM) to ASR tasks to overcome this problem. Our proposed ASR system is less vulnerable to external interference noise, and achieves a higher WRA compared to a conventional ASR system equipped with MFCCs and an HMM. The performance of our proposed ASR system was evaluated using a phonetically balanced word (PBW) set mixed with artificially added noise.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.801-804
• /
• 2001

This article is concerned with automatic segmentation of two adjacent vowels for speech signals. All kinds of transition case of adjacent vowels can be characterized by spectrogram. Firstly the voiced-speech is extracted by the histogram analysis of vowel indicator which consists of wavelet low pass components. Secondly given phonetic transcription and transition pattern spectrogram, the voiced-speech portion which has consecutive vowels automatically segmented by the template matching. The cross-correlation function is adapted as a template matching method and the modified correlation coefficient is calculated for all frames. The largest value on the modified correlation coefficient series indicates the boundary of two consecutive vowel sounds. The experiment is performed for 154 vowel transition sets. The 154 spectrogram templates are gathered from 154 words(PRW Speech DB) and the 161 test words(PBW Speech DB) which are uttered by 5 speakers were tested. The experimental result shows the validity of the method.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.50-59
• /
• 1997

In this paper, we implement an automatic speech segmentation and labeling system which marks phone boundaries automatically for constructing the Korean speech database. We specify and implement the system based on conventional speech segmentation and labeling techniques, and also develop the graphic user interface(GUI) on Hangul $Motif^{TM}$ environment for the users to examine the automatic alignment boundaries and to refine them easily. The developed system is applied to 16kHz sampled speech, and the labeling unit is composed of 46 phoneme-like units(PLUs) and silence. The system uses both of the phonetic and orthographic transcription as input methods of linguistic information. For pattern-matching method, hidden Markov models(HMM) is employed. Each phoneme model is trained using the manually segmented 445 phonetically balanced word (PBW) database. In order to evaluate the performance of the system, we test it using another database consisting of sentence-type speech. According to our experiment, 74.7% of phoneme boundaries are within 20ms of the true boundary and 92.8% are within 40ms.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.1
• /
• pp.18-30
• /
• 2021

The ultimate goal of the present study is to establish the acoustical performance standards of classroom for the elderly who are incomplete hearing people. As a pilot survey, the present study was conducted to investigate the listening environment and the actual condition of speech perception performance of education facilities for elderly, Acoustic performances of two education facilities for elderly in Cheongju were measured and questionnaire survey was done to elderly people. Also, speech intelligibility tests were undertaken by Consonant Vowel Consonant (CVC) and Phonetically Balanced Words (PBW) methods. The questionnaire survey showed that the elderly were satisfied with the listening environment of the educational facilities in general. Also, it was found that acoustical performances satisfy with the acoustic criteria of general classrooms in Korea. However, the results of the speech intelligibility test showed that the scores of elderly were significantly lower than twenties with normal hearing. It was also revealed that the scores are reduced as the age increases. Thus, it was concluded that the acoustical performance standards of educational facilities for the normal hearing were not suitable for educational facilities for the elderly.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.169-178
• /
• 2003

This study outlines two viewpoints the classification of phone likely unit (PLU) which is the foundation of korean large vocabulary speech recognition, and the effectiveness of Chiljongseong (7 Final Consonants) and Paljogseong (8 Final Consonants) of the korean language. The phone likely classifies the phoneme phonetically according to the location of and method of articulation, and about 50 phone-likely units are utilized in korean speech recognition. In this study auditory phonetical knowledge was applied to the classification of phone likely unit to present 45 phone likely unit. The vowels 'ㅔ, ㅐ'were classified as phone-likely of (ee) ; 'ㅒ, ㅖ' as [ye] ; and 'ㅚ, ㅙ, ㅞ' as [we]. Secondly, the Chiljongseong System of the draft for unified spelling system which is currently in use and the Paljongseonggajokyong of Korean script haerye were illustrated. The question on whether the phonetic value on 'ㄷ' and 'ㅅ' among the phonemes used in the final consonant of the korean fan guage is the same has been argued in the academic world for a long time. In this study, the transition stages of Korean consonants were investigated, and Ciljonseeng and Paljongseonggajokyong were utilized in speech recognition, and its effectiveness was verified. The experiment was divided into isolated word recognition and speech recognition, and in order to conduct the experiment PBW452 was used to test the isolated word recognition. The experiment was conducted on about 50 men and women - divided into 5 groups - and they vocalized 50 words each. As for the continuous speech recognition experiment to be utilized in the materialized stock exchange system, the sentence corpus of 71 stock exchange sentences and speech corpus vocalizing the sentences were collected and used 5 men and women each vocalized a sentence twice. As the result of the experiment, when the Paljongseonggajokyong was used as the consonant, the recognition performance elevated by an average of about 1.45% : and when phone likely unit with Paljongseonggajokyong and auditory phonetic applied simultaneously, was applied, the rate of recognition increased by an average of 1.5% to 2.02%. In the continuous speech recognition experiment, the recognition performance elevated by an average of about 1% to 2% than when the existing 49 or 56 phone likely units were utilized.