• 한국생산제조학회지
• /
• 제20권2호
• /
• pp.207-213
• /
• 2011

In this paper, we present a study on the real-time implementation of mobile robot to which the interactive voice recognition technique is applied. The speech command utters the sentential connected word and asserted through the wireless remote control system. We implement an automatic distance speech command recognition system for voice-enabled services interactively. We construct a baseline automatic speech command recognition system, where acoustic models are trained from speech utterances spoken by a microphone. In order to improve the performance of the baseline automatic speech recognition system, the acoustic models are adapted to adjust the spectral characteristics of speech according to different microphones and the environmental mismatches between cross talking and distance speech. We illustrate the performance of the developed speech recognition system by experiments. As a result, it is illustrated that the average rates of proposed speech recognition system shows about 95% above.

• 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.

• 음성과학
• /
• 제2권
• /
• pp.25-44
• /
• 1997

When listening the various speech synthesis systems developed and being used in our country, we find that though the quality of these systems has improved, they lack naturalness. Moreover, since the voice color of these systems are limited to only one recorded speech DB, it is necessary to record another speech DB to create different voice colors. 'Voice Color' is an abstract concept that characterizes voice personality. So speech synthesis systems need a voice color control function to create various voices. The aim of this study is to examine several factors of voice color control rules for the text-to-speech system which makes natural and various voice types for the sounding of synthetic speech. In order to find such rules from natural speech, glottal source parameters and frequency characteristics of the vocal tract for several voice colors have been studied. In this paper voice colors were catalogued as: deep, sonorous, thick, soft, harsh, high tone, shrill, and weak. For the voice source model, the LF-model was used and for the frequency characteristics of vocal tract, the formant frequencies, bandwidths, and amplitudes were used. These acoustic parameters were tested through multiple regression analysis to achieve the general relation between these parameters and voice colors.

• 대한후두음성언어의학회지
• /
• 제11권1호
• /
• pp.104-112
• /
• 2000

An evaluation of voice disorder has two methods. One is a perceptual analysis and the other is an acoustic analysis. All of these methods are just focused on sustained vowel. The analysis of conversational speech levels in voice disorder has not been achieved enough. The purpose of the present study is to compare two syllable words and sustained vowel in the vocal polyp patients and normal male speakers and to be applied on the vocal assessment and the voice therapy as a basic data. fifteen male patients with vocal polyp were the subject group. Fifteen healthy male were the control group for this study. The voices of the subject and control group, saved in MDVP of CSL were analyzed by its own analysis program. As a results, in subject group, the voice qualities between the vowel following lenis stop and the sustained vowel had no differences, and the voice qualities were different significantly between the vowel following heavily aspirated stop and the sustained vowel. In the control group the vowel fllowing stops and sustained vowel had also many differences in their voice quality, especially significant between the vowel following glottal stop and e sustained vowel.

• 말소리와 음성과학
• /
• 제10권2호
• /
• pp.77-84
• /
• 2018

The purpose of this study is to examine the acoustic characteristics of Parkinsonian speech, with respect to different utterance conditions, by employing acoustic/auditory-perceptual analysis. The subjects of the study were 15 patients (M=7, F=8) with Parkinson's disease who were asked to read out sentences under different utterance conditions (clear/casual). The sentences read out by each subject were recorded, and the recorded speech was subjected to cepstrum and spectrum analysis using Analysis of Dysphonia in Speech and Voice (ADSV). Additionally, auditory-perceptual evaluation of the recorded speech was conducted with respect to breathiness and loudness. Results indicate that in the case of clear speech, there was a statistically significant increase in the cepstral peak prominence (CPP), and a decrease in the L/H ratio SD (ratio of low to high frequency spectral energy SD) and CPP F0 SD values. In the auditory-perceptual evaluation, a decrease in breathiness and an increase in loudness were noted. Furthermore, CPP was found to be highly correlated to breathiness and loudness. This provides objective evidence of the immediate usefulness of clear speech intervention in improving the voice quality of Parkinsonian speech.

• 대한후두음성언어의학회지
• /
• 제7권1호
• /
• pp.32-38
• /
• 1996

The preservation of the voice-producing mechanism is an important feature in the management of laryngeal cancer by radiotherapy. But, radiation therapy has certain side effects such as mucositis, tissue edema, necrosis and fibrosis which could effect on normal voice production. Several subjective studies that used questionnaires and auditory perceptual judgements of voice have been interpreted to mean that radiation results in a normal or near-normal voice. Objective evidence of the status of vocal function after radiation treatment, however, is still lacking. We analyzed the changes that occur in voice parameters in a group of patients undergoing radiation therapy, in order to determine the effect of radiation on voice quality. In this study acoustic, aerodynamic measures of vocal function were used to determine the characteristics of voice production. We found that voice parameters in early glottic cancer changed meaningfully comparing to normal larynx with or without radiation and radiation therapy has an little effect on normal larynx.

• 한국컴퓨터정보학회논문지
• /
• 제19권11호
• /
• pp.159-166
• /
• 2014

본 논문에서는 감정을 통해 단어의 의미가 변화될 때 운율과 음질로 표현되는 음향 요소가 어떠한 역할을 하는지 분석한다. 이를 위해 6명의 발화자에 의해 5가지 감정 상태로 표현된 60개의 데이터를 이용하여 감정에 따른 운율과 음질의 변화를 살펴본다. 감정에 따른 운율과 음질의 변화를 찾기 위해 8개의 음향 요소를 분석하였으며, 각 감정 상태를 표현하는 주요한 요소를 판별 해석을 통해 통계적으로 분석한다. 그 결과 화남의 감정은 음의 세기 및 2차 포먼트 대역너비와 깊은 연관이 있음을 확인할 수 있었고, 기쁨의 감정은 2차와 3차 포먼트 값 및 음의 세기와 연관이 있으며, 슬픔은 음질 보다는 주로 음의 세기와 높낮이 정보에 영향을 받는 것을 확인할 수 있었으며, 공포는 음의 높낮이와 2차 포먼트 값 및 그 대역너비와 깊은 관계가 있음을 알 수 있었다. 이러한 결과는 감정 음성 인식 시스템뿐만 아니라, 감정 음성 합성 시스템에서도 적극 활용될 수 있을 것으로 예상된다.

• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.95-107
• /
• 2012

As BTX-A, which has been known to be the most effective treatment for ADSD, is not effective in treating vocal tremors, voice assessment must be employed to perform differential diagnosis of SD and vocal tremor in an accurate fashion. In this study, the characteristics of vocal changes after botulinum toxin injection were compared by analyzing the voice characteristics resulting from the presence of vocal tremors using objective analysis devices, with the aim of helping to provide prognoses and to determine remedial effects in clinical cases comprising patients with adductor spasmodic dysphonia accompanied by voice tremors. Respiratory function tests, aerodynamic analysis, electroglottography (EGG), acoustic analysis, auditory perception tests, and K-VHI had been conducted at intervals of four, eight, and twelve weeks before and after injection, targeting a group of 17 ADSD female patients (a ADSD group of four with vocal tremor and a ADSD group of 13 without voice tremor). For average FVC and FEV1, the T group showed statistically significant low averages compared with the NT group, whereas the T group showed statistically significant high average ATRI compared with the NT group. In addition, the T group showed a statistically significant Fatr, lower than that of the NT group. For the ADSD group of patients with voice tremor, their vocal tremor remained unchanged despite noticeable decrease in wringing voices. In other words, as the vocal tremor and wringing voices are two distinctive features, there is a need for the two features to be targeted separately for differential diagnosis.

• 말소리와 음성과학
• /
• 제15권4호
• /
• pp.45-51
• /
• 2023

나이가 들면서 발생하는 음성 문제는 사회적, 정서적으로 영향을 미칠 수 있으며, 나아가 고립감과 우울증으로 이어질 수 있다. 이에 본 연구에서는 노화로 인한 음향학적 특성 변화를 음질과 구어 유창성의 변화를 알아보고자 한다. 이를 위해 노년층 남성 20명과 청년층 남성 20명이 산출한 연장발성과 구절 읽기 과제를 녹음하여 분석하였다. 음질 분석 변수로 기본주파수(F0), 주기 변동률(jitter), 진폭 변동률(shimmer), 켑스트럼 정점(cepstral peak prominence, CPP) 값을 분석하였으며 구어 유창성 분석 변수로는 평균 음절 길이(average syllable duration, ASD), 조음 속도(articulation rate, AR), 구어 속도(SR)를 분석하였다. 연구결과, 음질 측정에서 노년층의 경우 F0가 높게 나타났으며 jitter, shimmer, CPP의 결과값을 통해 음질이 저하된 것으로 나타났다. 구어 유창성 분석 결과, 노년층은 ASD, AR, SR의 결과값을 통해 느리게 발화하는 것으로 나타났다. 음질과 구어유창성 간 상관관계 분석 결과, shimmer와 CPP 값과 각각 ASD와 SR에서 높은 상관관계가 나타났다. 본 연구결과를 통해 노화에 따른 음성과 구어 유창성 변화를 조기에 발견하고 이에 대한 적절한 훈련법을 제공할 수 있을 것으로 기대된다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 1998년도 춘계학술대회논문집; 용평리조트 타워콘도, 21-22 May 1998
• /
• pp.568-574
• /
• 1998

A systematic procedure for designing a direct-radiator-type loudspeaker has been developed, based on a numerical vibro-acoustic analysis and the Taguchi method. The finite-element model of the speaker cone has been used to calculate the vibration response of the cone excited by the voice coil. The vibration response of the speaker cone has been used as a boundary condition for the acoustic analysis, and the acoustic frequency characteristics of the loudspeaker have been calculated by the boundary element method. The numerical model has been confirmed by comparing the numerical results with experimental ones obtained in an anechoic chamber. Some design parameters contributing dominantly to the acoustic characteristics have been selected by using the Taguchi method, and the variations of the acoustic characteristics due to the changes of the parameter values have been examined using the numerical model.