• 제어로봇시스템학회논문지
• /
• 제16권12호
• /
• pp.1137-1142
• /
• 2010

This paper studied the speech parameters less affected by the human emotion for the development of the robust speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient and frequency warped mel-cepstral coefficient were used as feature parameters. And CMS (Cepstral Mean Subtraction) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using vocal tract length normalized mel-cepstral coefficient, its derivatives and CMS as a signal bias removal showed the best performance of 0.78% word error rate. This corresponds to about a 50% word error reduction as compare to the performance of baseline system using mel-cepstral coefficient, its derivatives and CMS.

• 말소리와 음성과학
• /
• 제7권1호
• /
• pp.21-26
• /
• 2015

The aim of this study is to synthesize pathological breathy voice and to make a cepstral peak prominence (CPP) table following breathiness ranks by cepstral analysis to supplement reliability of the perceptual auditory judgment task. KlattGrid synthesizer included in Praat was used. Synthesis parameters consist of two groups, i.e., constants and variables. Constant parameters are pitch, amplitude, flutter, open phase, oral formant and bandwidth. Variable parameters are breathiness (BR), aspiration amplitude (AH), and spectral tilt (TL). Five hundred sixty samples of synthetic breathy vowel /a/ for male were created. Three raters participated in ranking of the breathiness. 217 were proved to be inadequate samples from perceptual judgment and cepstral analysis. Finally, 343 samples were selected. These CPP values and other related parameters from cepstral analysis are classified under four breathiness ranks (B0~B3). The mean and standard deviation of CPP is $16.10{\pm}1.15$ dB(B0), $13.68{\pm}1.34$ dB(B1), $10.97{\pm}1.41$ dB(B2), and $3.03{\pm}4.07$ dB(B3). The value of CPP decreases toward the severe group of breathiness because there is a lot of noise and a small quantity of harmonics.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2002년도 11월 학술대회지
• /
• pp.115-118
• /
• 2002

Neural networks have been known to have great discriminative power in pattern classification problems. In this paper, the multilayer perceptron neural networks are employed to automatically detect laryngeal pathology in speech. Also new feature parameters are introduced which can reflect the periodicity of speech and its perturbation. These parameters and cepstral coefficients are used as input of the multilayer perceptron neural networks. According to the experiment using Korean disordered speech database, incorporation of new parameters with cepstral coefficients outperforms the case with only cepstral coefficients.

• 한국지능시스템학회논문지
• /
• 제22권6호
• /
• pp.681-686
• /
• 2012

본 논문에서는 강인한 감정 음성 인식 시스템을 개발하기 위하여 감정의 영향을 적게 받는 음성 파라메터에 대한 연구를 수행하였다. 이러한 목적을 위하여 다양한 감정이 포함된 데이터를 사용하여 감정이 음성 인식 시스템과 음성 파라메터에 미치는 영향을 분석하였다. 본 연구에서는 멜 켑스트럼, 델타 멜 켑스트럼, RASTA 멜 켑스트럼, 루트 켑스트럼, PLP 계수와 성도 길이 정규화 방법에서 주파수 와핑된 멜 켑스트럼 계수를 사용하였다. 또한 신호 편의 제거 방법으로 CMS 방법과 SBR 방법이 사용되었다. 실험결과에서 성도정규화 방법을 사용한 RASTA 멜 켑스트럼, 델타 멜 켑스트럼 및 CMS 방법을 사용한 경우가 HMM 기반의 화자독립 단독음 인식 실험 결과에서 가장 우수한 결과를 나타내었다.

• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.655-660
• /
• 2005

본 논문에서는 인간의 감정 변화에 강인한 음성 인식 기술 개발을 목표로 하여 감정 변화의 영향을 적게 받는 음성 인식시스템의 특징 파라메터에 관한 연구를 수행하였다. 이를 위하여 우선 다양한 감정이 포함된 음성 데이터베이스를 사용하여 감정 변화가 음성 인식 시스템의 성능에 미치는 영향에 관한 연구와 감정 변화의 영향을 적게 받는 음성 인식 시스템의 특징 파라메터에 관한 연구를 수행하였다. 본 연구에서는 LPC 켑스트럼 계수, 멜 켑스트럼 계수, 루트 켑스트럼 계수, PLP 계수와 RASTA 처리를 한 멜 켑스트럼 계수와 음성의 에너지를 사용하였다 또한 음성에 포함된 편의(bias)를 제거하는 방법으로 CMS와 SBR 방법을 사용하여 그 성능을 비교하였다. 실험 결과에서 RASTA 멜 켑스트럼과 델타 켑스트럼을 사용하고 신초편의 제거 방법으로 CMS를 사용한 경우에 HMM 기반의 화자독립 단어 인식기의 오차가 $7.05\%$로 가장 우수한 성능을 나타내었다. 이러한 것은 멜 켑스트럼을 사용한 기준시스템과 비교하여 $59\%$정도 오차가 감소된 것이다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2003년도 5월 학술대회지
• /
• pp.145-148
• /
• 2003

In this paper, we carried out comparative study about various feature parameters for the effective speaker recognition such as LPC, LPCC, MFCC, Log Area Ratio, Reflection Coefficients, Inverse Sine, and Delta Parameter. We also adopted cepstral liftering and cepstral mean subtraction methods to check their usefulness. Our recognition system is HMM based one with 4 connected-Korean-digit speech database. Various experimental results will help to select the most effective parameter for speaker recognition.

• 대한후두음성언어의학회지
• /
• 제14권2호
• /
• pp.110-116
• /
• 2003

Background and Objectives : Laryngeal cancer discrimination using voice signals is a non-invasive method that can carry out the examination rapidly and simply without giving discomfort to the patients. n appropriate analysis parameters and classifiers are developed, this method can be used effectively in various applications including telemedicine. This study examines voice analysis parameters used for laryngeal disease discrimination to help discriminate laryngeal diseases by voice signal analysis. The study also estimates the laryngeal cancer discrimination activity of the Gaussian mixture model (GMM) classifier based on the statistical modelling of voice analysis parameters. Materials and Methods : The Multi-dimensional voice program (MDVP) parameters, which have been widely used for the analysis of laryngeal cancer voice, sometimes fail to analyze the voice of a laryngeal cancer patient whose cycle is seriously damaged. Accordingly, it is necessary to develop a new method that enables an analysis of high reliability for the voice signals that cannot be analyzed by the MDVP. To conduct the experiments of laryngeal cancer discrimination, the authors used three types of voices collected at the Department of Otorhinorlaryngology, Pusan National University Hospital. 50 normal males voice data, 50 voices of males with benign laryngeal diseases and 105 voices of males laryngeal cancer. In addition, the experiment also included 11 voices data of males with laryngeal cancer that cannot be analyzed by the MDVP, Only monosyllabic vowel /a/ was used as voice data. Since there were only 11 voices of laryngeal cancer patients that cannot be analyzed by the MDVP, those voices were used only for discrimination. This study examined the linear predictive cepstral coefficients (LPCC) and the met-frequency cepstral coefficients (MFCC) that are the two major cepstrum analysis methods in the area of acoustic recognition. Results : The results showed that this met frequency scaling process was effective in acoustic recognition but not useful for laryngeal cancer discrimination. Accordingly, the linear frequency cepstral coefficients (LFCC) that excluded the met frequency scaling from the MFCC was introduced. The LFCC showed more excellent discrimination activity rather than the MFCC in predictability of laryngeal cancer. Conclusion : In conclusion, the parameters applied in this study could discriminate accurately even the terminal laryngeal cancer whose periodicity is disturbed. Also it is thought that future studies on various classification algorithms and parameters representing pathophysiology of vocal cords will make it possible to discriminate benign laryngeal diseases as well, in addition to laryngeal cancer.

• 말소리와 음성과학
• /
• 제6권2호
• /
• pp.47-54
• /
• 2014

The purpose of this study was to analyze spectral versus cepstral measurements in esophageal speakers. The comparison between the measurements in thirteen male esophageal speakers was compared with the control group of thirteen normal speakers using the sustained vowel /a/. The main results can be summarized as below: (a) the CPP and L/H ratio of the esophageal group were significantly lower than those of the control group (b) the CPP was significantly correlated with the spectral parameters such as jitter, shimmer, NHR and VTI, and (c) the ROC analysis showed that the threshold of 10.25dB for the CPP achieved a good classification for esophageal speakers, with 100% perfect sensitivity and specificity. Thus, it was known that cepstral-based acoustic measures such as CPP, may be more reliable predictors than other spectral-based acoustic measures such as jitter and shimmer. And it was found that cepstral-based acoustic measures were effective in distinguishing esophageal voice quality from normal voice quality. This research will contribute to establishing a baseline related to speech characteristics in voice rehabilitation with laryngectomees.

• 말소리와 음성과학
• /
• 제8권2호
• /
• pp.73-80
• /
• 2016

The purpose of this study was to analyze perceptual and spectral/cepstral measurements in patients with adductor spasmodic dysphonia(ADSD). Sixty participants with gender and age matched individuals(30 ADSD and 30 controls) were recorded in reading a sentence and sustained the vowel /a/. Acoustic data were analyzed acoustically by measuring CPP, L/H ratio, mean CPP F0 and CSID, and auditory-perceptual ratings were measured using GRBAS. The main results can be summarized as below: (a) the CSID for the connected speech was significantly higher than for the sustained vowel (b) the G, R and S for the connected speech were significantly higher than for the sustained vowel (c) Spectral/cepstral parameters were significantly correlated with the perceptual parameters, and (d) the ROC analysis showed that the threshold of 13.491 for the CSID achieved a good classification for ADSD, with 86.7% sensitivity and 96.7% specificity. Spectral and cepstral analysis for the connected speech is especially meaningful on cases where perceptual analysis and clinical evaluation alone are insufficient.

• 대한음성학회지:말소리
• /
• 제45호
• /
• pp.35-45
• /
• 2003

Laryngeal diseases cause significant changes in the quality of speech production. Automatic detection of laryngeal diseases by voice is attractive because of its nonintrusive nature. In this paper, we apply speech recognition techniques to detection of laryngeal cancer, and investigate which feature parameters and classification methods are appropriate for this purpose. Linear Predictive Cepstral Coefficients (LPCC) and Mel-Frequency Cepstral Coefficients (MFCC) are examined as feature parameters, and parameters reflecting the periodicity of speech and its perturbation are also considered. As for classifier, multilayer perceptron neural networks and Gaussian Mixture Models (GMM) are employed. According to our experiments, higher order LPCC with the periodic information parameters yields the best performance.