• Journal of Platform Technology
• /
• v.6 no.1
• /
• pp.3-8
• /
• 2018

This paper proposes a technique for recognizing online handwritten cursive data obtained by tracing a motion trajectory while a user is in the 3D space based on a convolution neural network (CNN) algorithm. There is a difficulty in recognizing the virtual character input by the user in the 3D space because it includes both the character stroke and the movement stroke. In this paper, we divide syllable into consonant and vowel units by using labeling technique in addition to the result of localizing letter stroke and movement stroke in the previous study. The coordinate information of the separated consonants and vowels are converted into image data, and Korean handwriting recognition was performed using a convolutional neural network. After learning the neural network using 1,680 syllables written by five hand writers, the accuracy is calculated by using the new hand writers who did not participate in the writing of training data. The accuracy of phoneme-based recognition is 98.9% based on convolutional neural network. The proposed method has the advantage of drastically reducing learning data compared to syllable-based learning.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.105-108
• /
• 2001

한국어 숫자는 각 숫자가 단음절로 이루어져 있으며, 연속적으로 발음될 때 인접 숫자들의 상호조음현상에 의해 각 숫자의 고유 발음이 변화하고, 또한 그 숫자들의 경계도 모호해지는 문제점이 있다. 한편 연속적인 숫자의 발성을 기대하는 인식시스템에 반하여 일부 사용자는 숫자들을 고려시켜서 발성하기도 한다. 이는 연결숫자의 음운현상만을 고려한 인식 시스템에서는 성능저하의 한 원인이 된다 본 논문에서는 연결숫자의 인식성능 향상을 위해서 한국어 숫자들의 음운 변화를 고려하여 변이음군을 정하였으며, 사용자의 여러 가지 발성형태에 따른 다양한 음운 현상의 변화를 흡수 할 수 있도록 인식 네트웍을 구성하는 방식을 검토하였다. 전화망 4연숫자음을 이용한 화자독립 인식실험을 통해서 한국어 숫자에서 자주 오인식 되는 '이', '오', '일' 인식 성능이 각각 $4..2\%$, $4.2\%$, $2.9\%$씩 향상되었으며, 인식속도도 $33\%$의 개선이 있었다

• Speech Sciences
• /
• v.9 no.4
• /
• pp.265-274
• /
• 2002

In this paper we propose an automatic segmentation system that outputs the time alignment information of phoneme boundary using Viterbi search with HMM (Hidden Markov Model) and corrects these results by an UVS (unvoiced/voiced/silence) classification algorithm. We selecte a set of 39 monophones and a set of 647 extended phones for HMM models. For the UVS classification we use the feature parameters such as ZCR (Zero Crossing Rate), log energy, spectral distribution. The result of forced alignment using the extended phone set is 11% better than that of the monophone set. The UVS classification algorithm shows high performance to correct the segmentation results.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.137-147
• /
• 2003

Speech synthesis can classify by synthesis way, that is waveform coding, source coding and mixture coding. Specially, waveform coding is suitable for high quality synthesis. However, it is not desirable by synthesis techniques of syllable or phoneme unit because it do not separate and handles excitation and formant part. Therefore, there is a need for pitch alteration method applied in synthesis by the rule in waveform coding. This study propose about pitch alteration method that use spectrum scaling after do to flatten spectra by subband linear approximation to minimize spectrum distortion. This paper show evaluation whether show excellency of some measure compared with LPC, Cepstrum, lifter function and method that propose. estimation method seeks distribution of each flattened signal and measured degree of flattened spectra Signal flattened is normalized, So that highest point amounts to zero, and distribution of signal ,whose average is zero, is calculated. this show result that measure the spectrum distortion rate to estimate performance of method that propose. The average spectrum distortion rate was kept below the average 2.12%, so the method that propose is superiors than existent method.

• The Journal of the Acoustical Society of Korea
• /
• v.3 no.2
• /
• pp.35-45
• /
• 1984

본 연구는 한국어의 발음상의 특징과 구조에 의해서 한국어를 음소별로 분리할 수 있음에 착안 하여, 자음과 모음으로 구성된 한국어 단음을 자음의 음소와 모음의 음소로 각각 분리하여 인식하는 새 로운 방법에 관한 연구이다. 특정 화자 2명에 대하여 한국어 단음 84자를 모음의 음소와 자음의 음소로 각각 분리하여 인삭한 실험결과 모음을 인식한 경우에는 선형 예측 계수를 이용하면 인식률이 95.2%이 고, 편자기 상관계수로 92.5%, 폴만트로 97.6%의 인식률을 얻었고, 자음을 인식한 경우에는 선형 예측 계수로 88.7%, 편자기 상관계수로 92.9%의 인식률을 얻었다. 또, 자음의 음소와 모음의 음소를 결합시킨 단음을 인식한 경우에는 선형 예측 계수로 83.9%, 편자기 상관계수로 86.3%의 인식률을 얻었다. 이 때, 각 음소들의 데이터의 수는 256개이고, 선형 예측 계수와 편자기 상관 계수와의 예측차는 15차이다. 이 와 같이 한국어를 자음의 음소와 모음의 음소로 분리하면 작은 데이터 양으로 처리 시간을 단축 시켜 한국어의 모든 단음, 단어, 연속음, 문장 등을 분석하고 인식할 수 있고, 또한 각 음소들을 원칙적으로 결합시켜 모든 한국어의 합성이 가능함을 알 수 있다.

• Speech Sciences
• /
• v.8 no.3
• /
• pp.185-200
• /
• 2001

This study was designed to investigate the treatment, generalization, and maintenance effects of vocal relaxation treatment on compensatory articulation(i.e., glottalization of plosive sound) of three children with cleft palate. Multiple baseline design was applied to evaluate treatment, generalization, and maintenance effects. The targeted phonemes were ph/, th/, /t/ which Were frequently substituted by glottal stop sounds. The main component of the treatment program was vocal relaxation using humming and aspiration sound /h/. The following conclusions were deduced from the results: (1) the treatment program for compensatory articulation was effective in facilitating correct production of targeted phoneme and eliminating glottalization for all subjects, (2) the treatment effects on articulation accuracy were generalized to untreated phonemes (/c/, /c$c^{h}$/) for 2 subjects, (3) the treatment effects on decrease of glottalization were generalized to untreated phonemes for all subjects, and (4) the treatment effects were maintained for all subjects for 2 weeks after treatment was terminated.

• Speech Sciences
• /
• v.8 no.3
• /
• pp.105-113
• /
• 2001

The abbreviation (specially, an acronym) are used more nowadays. However we are using them carelessly unknowing that there are some reducing patterns. In this paper, we will first analyse the right oralization and the phonemicization of abbreviation on the basis of the group types. Then, we will propose necessary and sufficient conditions to recognize how to read or pronounce the acronyms and in which way, when they are converted from the text to the speech. We have limited the use of acronym to the graphem-phoneme relations, and the diversity of the usage to minimized, and therefore we could define clearly the characteristics of the phonetic chains. In conclusion, we could find that there are more phonemicization in producing acronyms with these phonetic chains characteristics, and these phonetic based acronyms are increasingly used in the field of aviation and medicine.

• Speech Sciences
• /
• v.13 no.3
• /
• pp.169-183
• /
• 2006

The purpose of this study was to find an effect of Metaphon Intervention on the improvement of speech intelligibility of preschool children with articulation-phonological disorders. Subjects were 4 preschool children with articulation-phonological disorders. A multiple baseline design across subjects was used to examine the effect of the program. The program consisted of 2 steps. The first step was composed of concept level, sound level, phoneme level, and word level. The second step was on sentence level. Results were as follows: First, metaphon ability of all subjects was improved after the Metaphon Intervention. Second, speech intelligibility of all subjects was improved after Metaphon Intervention. From the results above, Metaphon Intervention can be effective to improve not only phonological awareness and metaphon but also overall speech intelligibility of preschool children with articulation-phonological disorders.

• Phonetics and Speech Sciences
• /
• v.2 no.4
• /
• pp.239-244
• /
• 2010

The purpose of this study is to investigate two phonological error patterns on coronal feature of children with functional articulation disorders and to compare them with those of general children. We tested 120 children with functional articulation disorders and 100 general children from 2~4 years of age with 'Assessment of Phonology & Articulation for Chidren(APAC)'. The results were as follows: (1) 37 disordered children substituted [+coronal] consonants for [-coronal] consonants (fronting of velars) and 9 disordered children substituted [-coronal] consonants for [+coronal] consonants (backing to velars). (2) Theses two phonological patterns were affected by the articulatory place of following phoneme. (3) The fronting pattern of children with articulation disorders was similar with that of general children, but their backing pattern was different with that of general children. These results show the clinical usefulness of coronal feature in phonological pattern analysis, the need of articulatory assessment with various phonetic context, and the importance of error contexts in clinical judgment.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.79-82
• /
• 2003

In this paper, we proposed Backgorund Model Set algorithm for the speaker verification to improve the shortcoming of calculating process in conventional confidence measure(CM). CM is to display relative likelihood between recognized models and unrecognized models. Unrecognized models is known as antiphone models. Calculate probability and standard deviation using all phonemes at process that compose antiphone model. At this process, antiphone CM brought bad result. Also, recognition time increases. In order problem, we studied about method to reconstitute average and standard deviation taking BMS algorithm using antiphoneme that near phoneme of CM calculation.