• Title/Summary/Keyword: speech inversion

Search Result 6, Processing Time 0.022 seconds

Development of articulatory estimation model using deep neural network (심층신경망을 이용한 조음 예측 모형 개발)

  • You, Heejo;Yang, Hyungwon;Kang, Jaekoo;Cho, Youngsun;Hwang, Sung Hah;Hong, Yeonjung;Cho, Yejin;Kim, Seohyun;Nam, Hosung
    • Phonetics and Speech Sciences
    • /
    • v.8 no.3
    • /
    • pp.31-38
    • /
    • 2016
  • Speech inversion (acoustic-to-articulatory mapping) is not a trivial problem, despite the importance, due to the highly non-linear and non-unique nature. This study aimed to investigate the performance of Deep Neural Network (DNN) compared to that of traditional Artificial Neural Network (ANN) to address the problem. The Wisconsin X-ray Microbeam Database was employed and the acoustic signal and articulatory pellet information were the input and output in the models. Results showed that the performance of ANN deteriorated as the number of hidden layers increased. In contrast, DNN showed lower and more stable RMS even up to 10 deep hidden layers, suggesting that DNN is capable of learning acoustic-articulatory inversion mapping more efficiently than ANN.

Laryngeal Closure Duration in Post-stroke Patients (뇌졸중 환자의 흡인유무에 따른 후두닫힘 지속시간)

  • Park, Tae-Ok;Ko, Do-Heung
    • Phonetics and Speech Sciences
    • /
    • v.2 no.2
    • /
    • pp.79-83
    • /
    • 2010
  • As bolus enters the pharynx during the swallow, laryngeal closure takes place by approximating the epiglottis to the arytenoid Laryngeal Closure Duration(LCD) is the duration of contact between the arytenoids and the epiglottis from the first contact to the last(Logemann et al, 2000). Epiglottic inversion continues pharyngeal swallow stage is completed in order to protect the airway. The purpose of this study is to measure layrngeal closure duration (LCD) in three groups of subjects: a) 10 stroke patients who aspirate before and during the swallow(aspirators), b) 10 stroke patients who do not aspirate during the swallow c)10 normal control subjects. Means and standard deviation of LCD was analyzed in both 5ml and 10 ml thin liquids using 100msec timer in videoflouroscopic swallowing examination. The mean for each group was 0.15 seconds shorter from aspirators to control group. There was a significant difference between aspirators and normal subjects for laryngeal closure duration during the swallow. Laryngeal closure duration after a stroke lead to aspiration. However, only one of this temporal problem may not be enough to aspiration.

  • PDF

Improvement of the Linear Predictive Coding with Windowed Autocorrelation (윈도우가 적용된 자기상관에 의한 선형예측부호의 개선)

  • Lee, Chang-Young;Lee, Chai-Bong
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.6 no.2
    • /
    • pp.186-192
    • /
    • 2011
  • In this paper, we propose a new procedure for improvement of the linear predictive coding. To reduce the error power incurred by the coding, we interchanged the order of the two procedures of windowing on the signal and linear prediction. This scheme corresponds to LPC extraction with windowed autocorrelation. The proposed method requires more calculational time because it necessitates matrix inversion on more parameters than the conventional technique where an efficient Levinson-Durbin recursive procedure is applicable with smaller parameters. Experimental test over various speech phonemes showed, however, that our procedure yields about 5 % less power distortion compared to the conventional technique. Consequently, the proposed method in this paper is thought to be preferable to the conventional technique as far as the fidelity is concerned. In a separate study of speaker-dependent speech recognition test for 50 isolated words pronounced by 40 people, our approach yielded better performance too.

A Comparison of Meter in Amoretti and Sonnets from the Portuguese (Amoretti와 Sonnets from the Portuguese의 율격 비교)

  • Sohn, Il-Kwon
    • MALSORI
    • /
    • no.63
    • /
    • pp.23-46
    • /
    • 2007
  • The purpose of this paper is to compare linguistic features of meter in Amoretti and Sonnets from the Portuguese. Amoretti was composed in the 16th century and Sonnets from the Portuguese in the 19th century. Two poems are very strict in satisfying $^*<_I$(LS that makes a lexical stress matched on a strong position. But they allow a peaked monosyllabic word to be matched on a weak position only if it does not violate $^*(\dot{\sigma}\;{\sigma})$. Syntactic inversions which are found in two poems occur to satisfy metrical constraints and rhyme. Particularly, syntactic inversions for rhyme are mainly found in Amoretti, but are rare in Sonnets from the Portuguese which includes many enjambment lines. Furthermore, this paper shows that syntactic inversions can be explained by the interaction of constraints, such as metrical constraints, SCI, and Binary Foot.

  • PDF

An approximated implementation of affine projection algorithm using Gram-Scheme orthogonalization (Gram-Schmidt 직교화를 이용한 affine projection 알고리즘의 근사적 구현)

  • 김은숙;정양원;박선준;박영철;윤대희
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.24 no.9B
    • /
    • pp.1785-1794
    • /
    • 1999
  • The affine projection algorithm has known t require less computational complexity than RLS but have much faster convergence than NLMS for speech-like input signals. But the affine projection algorithm is still much more computationally demanding than the LMS algorithm because it requires the matrix inversion. In this paper, we show that the affine projection algorithm can be realized with the Gram-Schmidt orthogonalizaion of input vectors. Using the derived relation, we propose an approximate but much more efficient implementation of the affine projection algorithm. Simulation results show that the proposed algorithm has the convergence speed that is comparable to the affine projection algorithm with only a slight extra calculation complexity beyond that of NLMS.

  • PDF

The bibliographical study on the senile dementia (노인성치매(老人性痴呆)에 대(對)한 문헌적(文獻的) 고찰(考察))

  • Kim, Hyun-Ah;Jeong, Ji-Cheon;Lee, Won-Chel
    • The Journal of Internal Korean Medicine
    • /
    • v.13 no.2
    • /
    • pp.57-69
    • /
    • 1992
  • The study has been carried out to investigate of the senile dementia by referring to 35 literratures. The results were as follows ; 1. In oriental medical science, senile dementia is belong to the category of dullness(매病), insanity(癲狂證), weak(虛勞), amnesia(健忘), etc. 2. The cause of senile dementia summarize the phlegm preventid-heart hole(痰迷心竅), marrow lack(髓海不足), aged follow weaking of body and disfunction of the internal organs(年老體弱과 臟腑機能 失調), the bad blood with vatal block(氣滯血瘀), feeling inharmony, etc in the view of oriental medical science and make the vanishment of the cerebral atrophy and the cerebral cell but havn't indicated the remarkable cause in that of western medical science. The diseases with cause make a point of Alzheimer's dementia, frequent infarction dementia, etc and psychological and environmental factor too. The marrow lack is related to Alzheimer's dementia, the feeling inharmony, psychologic and environmental factor, the phlegm prevented-heart hole and bad blood with vatal block, frequent infarction dementia. 3. The senile dementia is related cleary to the function of the internal organs in oriental medical sciences respect Especially in relation to kidney and marrow, it is presented new cause view to solve the cure problem of western medical science is studying its cause only the anatomic pathology with cerebrum and is thinking to solve cure possibility. 4. The symptom of senile dementia is as follows. The obstacle of a aspect of the Language, Emotion, Behavior. mute, speech inversion, sometimes a laugh sometimes a cry, behavior strange, failure of memory etc. 5. The treatment of senile dementia is follows. The methodes of cure apply phlegm changed-mud(豁痰化濁), self-kidney and added marrow(補腎益髓), self-energy and nutritive blood(益氣補血), vital blood(祛瘀活血), peace of mind and relief(安神情志). The medicines of cure make the most of (sesimtang, jwagui-hwan, tonggwuhwalhuel tang) add and subtract, daeboweonjeon, guibitang, and so on.

  • PDF