• The Journal of the Acoustical Society of Korea
• /
• v.14 no.3
• /
• pp.61-70
• /
• 1995

In this paper, the PLP cepstrum which is close to human perceptual characteristics was extracted through the spread time area to get the temperal feature. Phonemes were recognized by artificial neural network similar to the learning method of human. The phoneme strings were matched by Markov models which well suited for sequence. Phoneme recognition for the continuous Korean speech had been done using speech blocks in which speech frames were gathered with unequal numbers. We parameterized the blocks using 7th order PLPs, PTP, zero crossing rate and energy, which neural network used as inputs. The 100 data composed of 10 Korean sentences which were taken from the speech two men pronounced five times for each sentence were used for the the recognition. As a result, maximum recognition rate of 94.4% was obtained. The sentence was recognized using Markov models generated by the phoneme strings recognized from earlier results the recognition for the 200 data which two men sounded 10 times for each sentence had been carried out. The sentence recognition rate of 92.5% was obtained.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.735-742
• /
• 2019

In this paper, we propose a method of extracting speech features for phoneme recognition based on spikegram. The Fourier-transform-based features are widely used in phoneme recognition, but they are not extracted in a biologically plausible way and cannot have high temporal resolution due to the frame-based operation. For better phoneme recognition, therefore, it is desirable to have a new method of extracting speech features, which analyzes speech signal in high temporal resolution following the model of human auditory system. In this paper, we analyze speech signal based on a spikegram that models feature extraction and transmission in auditory system, and then propose a method of feature extraction from the spikegram for phoneme recognition. We evaluate the performance of proposed features by using a DNN-based phoneme recognizer and confirm that the proposed features provide better performance than the Fourier-transform-based features for short-length phonemes. From this result, we can verify the feasibility of new speech features extracted based on auditory model for phoneme recognition.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.277-280
• /
• 2001

본 연구에서는 연속음성인식 시스템의 성능개선을 위한 기초 연구로서 음소결정트리 상태분할과 한국어 음성학적 지식을 이용하여 문맥의존 음향모델의 작성방법을 검토하고. 한국어 연속음성인식에 적용을 소개한다. 음소결정트리 상태분할 알고리즘은 각 노드에서 한국어 음성학적 지식으로 구성된 음소 질의어 집합에 따라 2진 트리로 SSS(Successive State Splitting) 알고리즘에 의해 상태분할 하는 방법으로서 상태분할 후 각 상태를 네트워크로 연결한 구조를 HM-Net(Hidden Markow Network)이라 하며 문맥의존 음향모델로 표현된다. 작성한 문맥의존 음향모델의 유효성을 확인하기 위해 본 연구실의 항공편 예약 문장(YNU200)에 대해 연속음성인식 실험을 수행하였다. 인식실험 결과, 문맥의존 음향모델에 대한 화자독립 연속음성인식률이 기존의 단일 HMM 모델보다 평균적으로 1-pass의 경우 9.9%, 2-pass의 경우 4.1% 향상된 인식률을 보였다. 따라서 문맥의존 음향모델을 작성하는데 음소결정트리 상태분할과 한국어 음성학적 지식이 유효함을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.31-39
• /
• 1995

In this paper, we have constructed phoneme discriminant filters [PDF] according to the linear discriminant function. These discriminant filters do not follow the heuristic rules by the experts but the mathematical methods in iterative learning. Proposed system. is based on the piecewise linear classifier and error correction learning method. The segmentation of speech and the classification of phoneme are carried out simutaneously by the PDF. Because each of them operates independently, some speech intervals may have multiple outputs. Therefore, we introduce the unified coefficients by the output unification process. But sometimes the output has a region which shows no response, or insensitive. So we propose time windows and median filters to remove such problems. We have trained this system with the 549 monosyllables uttered 3 times by 3 male speakers. After we detect the endpoint of speech signal using threshold value and zero crossing rate, the vowels and consonants are separated by the PDF, and then selected phoneme passes through the following PDF. Finally this system unifies the outputs for competitive region or insensitive area using time window and median filter.

• The Journal of the Acoustical Society of Korea
• /
• v.6 no.3
• /
• pp.60-67
• /
• 1987

In this paper, a phoneme classification method for Korean speech recognition has been proposed and its performance has been studied. The phoneme classification has been done based on the phonemic features extracted by the prewindowed recursive least-square (PRLS) algorithm that is a kind of adaptive filter algorithms. Applying the PRLS algorithm to input speech signal, precise detection of phoneme boundaries has been made, Reference patterns of Korean phonemes have been generated by the ordinery vector quantization (VQ) of feature vectors obtained manualy from prototype regions of each phoneme. In order to obtain the performance of the proposed phoneme classification method, the method has been tested using spoken names of seven Korean cities which have eleven different consonants and eight different vowels. In the speaker-dependent phoneme classification, the accuracy is about $85\%$ considering simple phonemic rules of Korean language, while the accuracy of the speaker-independent case is far less than that of the speaker-dependent case.

• The Journal of the Acoustical Society of Korea
• /
• v.6 no.2
• /
• pp.38-47
• /
• 1987

As Korean language can be phonemically classified according to the characteristic and structure of its pronunciation, Korean syllables can be divided into the phonemes such as consonant and vowel. The divided phonemes are analyzed by using the method of partial autocorrelation, and the order of partial autocorelation coefficient is 15. In analysis, it is shown that each characteristic of the same consonants, vowels, and end consonant in syllables in similar. The experiments is carried out by dividing 675 syllables into consonants, vowels, and end consonants. The recognition rate of consonants, vowels, end-consonants, and syllables are $85.0(\%)$, $90.7(\%)$, $85.5(\%)$and $72.1(\%)$ respectively. In conclusion, it is shown that Korean syllables, divided by the phonemes, are analyzed and recognized with minimum data and short processing time. Furthermore, it is shown that Korean syllables, words and sentences are recognized in the same way.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.1
• /
• pp.81-87
• /
• 1989

This paper discribes the method associated with modeling of Korean phonemes. Hidden Markov models(HMM's) may be viewed as an effective technique for modeling the inherent nonstationarity of speech signal. We propose a 3-state phoneme model to represent the sequentially changing characteristics of phonemes, i.e., transition-to-stationary-to-transition. Also we clarify that the duration of a phoneme is an important factor to have an effect in recognition accuracy and show that improvement in recognition rate can be obtained by using duration-dependent 3-state hidden Markov models.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1997.06a
• /
• pp.35-39
• /
• 1997

본 연구에서는 음소를 인식의 기본단위로 하는 한국어 단어인식 시스템의 인식정도를 개선하기 이해 각 음소의 시간방향의 정보를 포함하고 있는 동적특징인 회귀계수와 K-L(Karhunen-Loeve)변환으로 얻은 특징파라미터(이하 K-L계수라 함)를 이용하여 음소인식과 단어인식 실험을 수행한 결과 그 유효성을 확인하였다. 이를 위해 먼저 파열음을 대상으로 정적 특징과 파라미터인 멜-켑스트럼(Mel-Cepstrum)과 동적 특징 파라미터인 회귀계수(Regressive Coefficient) 와 K-L 계수(Karhunen-Loeve Coefficient)를 추출하여 음소 인식실험을 수행하였다. 그 결과 멜-켑스트럼을 사용한 경우 39.84%, 회귀계수를 사용한 경우 48.52%, K-L계수를 사용한 경우 52.40%의 인식률을 얻었다. 이를 참고로 각각의 특징 파라미터를 결합하여 인식실험한 결과 멜-켑스트럼과 K-L계수를 사용한 경우 47.17%,멜 -켑스트럼과 회귀계수의 경우 60.11%,K-L계수와 회귀계수의 경우 60.35%, 멜-켑스트럼과 K-L계수 , 회귀계수를 사용한 경우 58.13%를 인식률을 얻어 동적특징인 K-L 계수와 회귀계수를 사용한 경우와 멜-켑스트럼과 회귀계수를 사용한 경우가 높은 인식률을 보였으며 이를 단어로 확장하여 인식실험을 수행한 결과 기존의 특징 파라미터를 이용한 경우보다 높은 인식률을 얻어 동적 파라미터의 유효성을 확인하였다

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.101-112
• /
• 1995

In order to construct a feature map-based phoneme classification system for speech recognition, two procedures are usually required. One is clustering and the other is labeling. In this paper, we present a phoneme classification system based on the Kohonen's Self-Organizing Feature Map (SOFM) for clusterer and labeler. It is known that the SOFM performs self-organizing process by which optimal local topographical mapping of the signal space and yields a reasonably high accuracy in recognition tasks. Consequently, SOFM can effectively be applied to the recognition of phonemes. Besides to improve the performance of the phoneme classification system, we propose the learning algorithm combined with the classical K-mans clustering algorithm in fine-tuning stage. In order to evaluate the performance of the proposed phoneme classification algorithm, we first use totaly 43 phonemes which construct six intra-class feature maps for six different phoneme classes. From the speaker-dependent phoneme classification tests using these six feature maps, we obtain recognition rate of $87.2\%$ and confirm that the proposed algorithm is an efficient method for improvement of recognition performance and convergence speed.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.85-93
• /
• 2011

Previous existing vocabulary recognition programs calculate general vector values from a database, so they can not process phonemes that form during a search. And because they can not create a model for phoneme data, the accuracy of the Gaussian model can not secure. Therefore, in this paper, we recommend use of the Bhattacharyya distance measurement method based on the features of the phoneme-thus allowing us to improve the recognition rate by picking up accurate phonemes and minimizing recognition of similar and erroneous phonemes. We test the Gaussian model optimization through share continuous probability distribution, and we confirm the heighten recognition rate. The Bhattacharyya distance measurement method suggest in this paper reflect an average 1.9% improvement in performance compare to previous methods, and it has average 2.9% improvement based on reliability in recognition rate.