• The Journal of the Acoustical Society of Korea
• /
• 제18권1E호
• /
• pp.3-6
• /
• 1999

In digital mobile communication system, the transmission errors affect the quality of output speech seriously. There are many error concealment techniques using a posteriori probability which provides information about any transmitted parameter. They need knowledge about channel transition probability as well as the 1st order Markov transition probability of codec parameters for estimation of transmitted parameters. However, in applications of mobile communication systems, the channel transition probability varies depending on nonstationary channel characteristics. The mismatch of designed channel transition probability of the estimator to actual channel transition probability degrades the performance of the estimator. In this paper, we proposed a new parameter estimator which adapts to the channel characteristics using short time average of maximum a posteriori probabilities(MAPs). The proposed scheme, when applied to the LSP parameter estimation, performed better than the conventional estimator which do not adapt to the channel characteristics.

• 대한음성학회지:말소리
• /
• 제44호
• /
• pp.83-92
• /
• 2002

Speech recognition performance is severly degraded under noisy envrionments. One approach to cope with this problem is audio-visual speech recognition. In this paper, we discuss the experiment results of bimodal speech recongition based on enhanced speech feature vectors using lip information. We try various kinds of speech features as like linear predicion coefficient, cepstrum, log area ratio and etc for transforming lip information into speech parameters. The experimental results show that the cepstrum parameter is the best feature in the point of reconition rate. Also, we present the desirable weighting values of audio and visual informations depending on signal-to-noiso ratio.

• 대한음성학회지:말소리
• /
• 제48호
• /
• pp.107-116
• /
• 2003

This paper deals with a new parameter for voice detection which is used for many areas of speech engineering such as speech synthesis, speech recognition and speech coding. CV (Coefficient of Variation) of speech spectrum as well as other feature parameters is used for the detection of speech. CV is calculated only in the specific range of speech spectrum. Average magnitude and spectral magnitude are also employed to improve the performance of detector. From the experimental results the proposed voice detector outperformed the conventional energy-based detector in the sense of error measurements.

• 대한전기학회논문지
• /
• 제41권2호
• /
• pp.209-216
• /
• 1992

Deafs train articulation by observing mouth of a tutor, sensing tactually the motions of the vocal organs, or using speech training aids. Present speech training aids for deafs can measure only single speech parameter, or display only frequency spectra in histogram of pseudo-color. In this study, a speech training aids that can display subject's articulation in the form of a cross section of the vocal organs and other speech parameters together in a single system is to be developed and this system makes a subject know where to correct. For our objective, first, speech production mechanism is assumed to be AR model in order to estimate articulatory motions of the vocal organs from speech signal. Next, a vocal tract profile model using LP analysis is made up. And using this model, articulatory motions for Korean vowels are estimated and displayed in the vocal tract profile graphics.

• 한국음향학회지
• /
• 제31권8호
• /
• pp.487-506
• /
• 2012

This paper proposes a speech enhancement algorithm to improve the speech intelligibility by suppressing both reverberation and background noise. The algorithm adopts a non-causal single-channel minimum variance distortionless response (MVDR) filter to exploit an additional information that is included in the noisy-reverberant signals in subsequent frames. The noisy-reverberant signals are decomposed into the parts of the desired signal and the interference that is not correlated to the desired signal. Then, the filter equation is derived based on the MVDR criterion to minimize the residual interference without bringing speech distortion. The estimation of the correlation parameter, which plays an important role to determine the overall performance of the system, is mathematically derived based on the general statistical reverberation model. Furthermore, the practical implementation methods to estimate sub-parameters required to estimate the correlation parameter are developed. The efficiency of the proposed enhancement algorithm is verified by performance evaluation. From the results, the proposed algorithm achieves significant performance improvement in all studied conditions and shows the superiority especially for the severely noisy and strongly reverberant environment.

• 말소리와 음성과학
• /
• 제5권4호
• /
• pp.17-24
• /
• 2013

This study is aimed at finding out different types of speech characteristics categorized based on voice rehabilitation techniques used on twenty-six patients (all-male) with total or partial laryngectomees. The speech intelligibility of standard esophageal (SE), tracheoesophageal speech (TE), and electriclarynx (EL) was measured by using the CSL and eleven listeners were instructed to rate the speech on a 5-point scale. The vowel space parameters such as vowel space, VAI, FCR, and F2 ratio were measured by averaging 5 repeats of each vowel (/a/, /e/, /i/, /u/) and the results were put into the parameter formula. The results showed significant statistical differences in speech intelligibility and vowel space between SE and TE. The speech intelligibility and vowel space of TE were higher than those of SE or EL and there was a high correlation between speech intelligibility and some parameters (vowel space, VAI, F2 ratio). The results also showed that TE's speech characteristics were most similar to normal groups comparing with SE and EL, but still very deviant in laryngeal speech. This was due to insufficient airflow intake into the esophagus when producing sounds, and because articulation movement was carried out differently among groups. Therefore, these findings will contribute to establishing a baseline related to speech characteristics in voice rehabilitation for patients with alaryngeal speech.

• 음성과학
• /
• 제10권3호
• /
• pp.29-36
• /
• 2003

The purposes of this study was to conduct a correlational analysis among $F_^{0}$, Jitter, Shimmer, and NHR (HNR), and NNE estimated by three speech analysis softwares, MDVP, Praat and Dr. Speech. Thirty females and 15 males with normal voice participated in the study. We used Sound Forge 6.0 to record their voice. MDVP, Praat and Dr. Speech were used to measure the acoustic parameters. The Pearson correlation coefficient was determined through a statistical analysis. The results came out as follows: Firstly, there was a strong correlation between $F_^{0}$ and Shimmer of both instruments. However, there was no correlation between Jitter of both instruments. Secondly, Shimmer showed a stronger correlation with HNR, NHR, and NNE than Jitter. Therefore, Shimmer was considered to be more useful and sensitive parameter to identify dysphonic voice compared to jitter.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.63-66
• /
• 2005

For the Large Corpus based TTS the consistency of the speech corpus is very important. It is because the inconsistency of the speech quality in the corpus may result in a distortion at the concatenation point. And because of this inconsistency, large corpus must be tuned repeatedly One of the reasons for the inconsistency of the speech corpus is the different glottal characteristics of the speech sentence in the corpus. In this paper, we adjusted the glottal characteristics of the speech in the corpus to prevent this distortion. And the experimental results are showed.

• 한국음향학회지
• /
• 제25권8호
• /
• pp.383-388
• /
• 2006

본 논문에서는 잡음 환경에서 단일 마이크로폰의 음성 향상에 대한 새로운 기법을 제시했다. 일반적으로 널리 알려진 스펙트럼 차감법에 근거한 음성 향상 기술은 신호 대 잡음비에 따른 스펙트럼 이득으로 표현된다. 대표적인 Ephraim과 Malah의 decision-directed (DD) 추정치는 잡음 구간에서 효율적으로 뮤지컬 잡음을 제거하지만 음성 구간에서는 이전 프레임의 음성 스펙트럼 성분에 더 큰 비중을 두기 때문에 a priori SNR의 프레임 지연이 발생한다. 따라서 DD에 의해 추정된 a priori SNR이 적용된 잡음 제거 이득은 현재 프레임보다 이전 프레임에 영향을 받으므로 음성 전이 구간에서 잡음 제거 성능을 저하시킨다. 본 논문은 DD의 가중치 파라미터에 Sigmoid Type의 함수를 적용하여 계산적으로는 간단하지만 효과적인 음성 향상 알고리즘을 제안한다. 제안된 접근 방식은 DD의 주요 파라미터인 a priori SNR 지연의 문제점을 해결하면서 뮤지컬 잡음 제거에 우수한 DD의 이점은 유지한다. 제안된 알고리즘의 성능은 다양한 잡음 환경에서 ITU-T P.862 Perceptual Evaluation of Speech Quality (PESQ) 와 Mean Opinion Score (MOS). 그리고 음성 스펙트로그램 (Spectrogram)에 의해 평가했고 기존의 DD의 고정된 가중치 파라미터를 사용했을 때 보다 향상된 결과를 나타내었다.

• 대한전자공학회논문지SP
• /
• 제38권5호
• /
• pp.567-575
• /
• 2001

본 논문에서는 음성신호의 발성길이와 상관없이 일정한 크기의 파라미터를 얻을 수 있는 새로운 방법을 제안하였다. 음성인식기의 성능은 음성신호에서 추출된 파라미터간의 유사도(패턴간의 거리)를 어떻게 비교하는지에 따라 결정된다. 그러나 화자에 따른 음성신호의 변이나 발성속도의 차이는 음성신호에서 일정한 크기의 파라미터 추출을 어렵게 한다. 제안한 방법은 음성신호에서 얻어진 파라미터를 스펙토그램의 형태로 표현한 뒤 2차원 DCT(Discrete Cosine Transform)를 이용해 일정한 크기의 파라미터로 정규화시키는 방법이다. 제안한 방법의 유효성을 입증하기 위해 청각세포를 모델링한 32개의 대역통과 필터로부터 얻어진 음성신호의 파라미터를 2차원 DCT 방법으로 가공한 후, 신경 회로망의 입력으로 사용하였다. 또한 기존 방법과의 인식률 비교를 위해 기존의 정규화된 입력을 구하는 방법 중 하나를 선택하여 비교 실험을 수행하였다. 실험결과 제안한 방법은 기존 방법에 비해 화자종속 및 화자독립 고립단어 인식에서 더 높은 인식률과 빠른 인식속도를 얻을 수 있었다.