• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.187-190
• /
• 2000

In this paper, implementation of speech Recognizer system, Separated from Personal computer. By using DSP, this intends to extend the voice recognizing, limited into PC because of amount of data and calculations. For this performance The thesis uses the real time End point detector and organizes no additional device between human and the system, characteristic vector are that detects End point and voice from absolute energy and ZCR, that uses 12 difference Cepstrum from LPC, that uses the method to compensate the process of pattern separating and pre-calculated standard pattern limitation.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 2006년도 하계종합학술발표회 논문 초록집
• /
• pp.438-438
• /
• 2006

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1996년도 영남지부 학술발표회 논문집 Acoustic Society of Korean Youngnam Chapter Symposium Proceedings
• /
• pp.70-75
• /
• 1996

In this paper, the pre-precessing method for the recognition of single vowels by use of spectrum envelope is presented , we use new method of an extrating spectrum envelope using the diffusion filter bank. We reduced the total processing time, and got higher enhancement of discrimination . By getting 88.3% of average recognition rate for single vowels of real voice through computer simulation, we confirmed it to be useful for speech recongition which use spectrum analysis for voice signal to have many frequency components.

• 한국멀티미디어학회논문지
• /
• 제8권1호
• /
• pp.56-61
• /
• 2005

본 논문은 연속음성인식을 위한 음성구간과 피치를 검출하는 알고리즘을 제안한다. 이것은 연속음성을 입력받아 프레임 단위로 자/모음을 구분하며, 구분된 유성음에서 피치를 검출하는 방법이다 실제 잡음 환경에서 음성을 입력받아 적당한 문턱치 에너지를 사용함으로써 잡음환경에서 강인한 음성구간 추출이 가능하였고 추출한 음성구간에서 프레임단위로 영교차율과 단구간에너지를 이용한 알고리즘으로 유성음의 피치를 검출함과 동시에 자/모음을 구분하는 개선된 방식이다.

• 한국정밀공학회지
• /
• 제23권5호
• /
• pp.68-76
• /
• 2006

The ability to recognize human emotion is one of the hallmarks of human-robot interaction. Hence this paper describes the realization of emotion recognition. For emotion recognition from voice, we propose a new feature called frequency range of meaningful signal. With this feature, we reached average recognition rate of 76% in speaker-dependent. From the experimental results, we confirm the usefulness of the proposed feature. We also define the noise environment and conduct the noise-environment test. In contrast to other features, the proposed feature is robust in a noise-environment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1988년도 전기.전자공학 학술대회 논문집
• /
• pp.723-726
• /
• 1988

This paper is a study about the automatic control of wheelchairs. This is realized by joystick, and is simulated by voice signal recognition. The control system by joystick is designed as follows: joystick paddle is connected with a timer and this timer ouput is high only when the joystick is moved. A computer reads the duration of this high state, and ouputs motor control word decided from this value using look-up table. The control system by voice signal is designed as follows: partial autocorrelation coefficients are computed from A/D converted signals and these values are compared with referance patterns. From this, the motor control word is decided on by the neareast neighbor rule.

• 산업기술연구
• /
• 제29권A호
• /
• pp.95-100
• /
• 2009

In this paper, we implemented a speaker-independent speech recognizer using the TMS320F28335 DSP which is optimized for control applications. For this implementation, we used a small-sized commercial DSP module and developed a peripheral board including a codec, signal conditioning circuits and I/O interfaces. The speech signal digitized by the TLV320AIC23 codec is analyzed based on MFCC feature extraction methed and recognized using the continuous-density HMM. Thanks to the internal SRAM and flash memory on the TMS320F28335 DSP, we did not need any external memory devices. The internal flash memory contains ADPCM data for voice response as well as HMM data. Since the TMS320F28335 DSP is optimized for control applications, the recognizer may play a good role in the voice-activated control areas in aspect that it can integrate speech recognition capability and inherent control functions into the single DSP.

• 전자공학회논문지B
• /
• 제30B권5호
• /
• pp.73-81
• /
• 1993

We have developed a system which can analyze the status of signal sent from/received to a signalling service equipment within the fully electronic switching system such as TDX-10. The system has such functions that acquire PCM signal of the preferred channel from the subhighway of the thirth-two channel by which a Universal Signal Tr ansceiver Unit(USTU) is connected with Time Switch Unit (TSU), and then classify the type of signal such as R2MFC/DTMF/CCT/VOICE, and determine the digit. Up to now, we have analyzed the frequency spec trum using the FFT. This paper describes the developement of PCM acquirer which can analyze the signal characteristics by acquiring the PCM signal in SHW(subhighway), and proposes the CZT(Chirp Z-Transform) algorithm. An algorithm which analyzes the acquired signal and determines the signal frequency and the corresponding power spectrum using the CZT is also discussed here.

• 한국전자통신학회논문지
• /
• 제8권1호
• /
• pp.77-83
• /
• 2013

본 논문에서는 음성 인식률 개선에 관한 방법을 제시하고 연구하였다. 기존의 음성 검출 방법 중 많이 이용되고 있는 HMM(Hidden Markov Model) 알고리즘을 이용하여서 음성을 검출하였다. 실험은 음성 검출과 음성 인식의 두 가지 방법으로 진행하였다. 음성 검출은 음성의 단위로 영교차율을 구하여 데이터의 유무를 판별하였다. 음성 인식은 음성의 형상의 패턴을 분석한 후 학습된 패턴과 비교 하는 형식으로 분석하였다. 실험 결과, 제안된 음성 형상의 패턴인식 이용한 알고리즘은 92%의 음성 인식률을 얻어 80%의 기존 HMM 알고리즘에 비해서 약 12%의 향상된 인식률을 얻을 수 있었다.

• 정보처리학회논문지B
• /
• 제18B권6호
• /
• pp.397-404
• /
• 2011

본 논문에서는 헬륨가스 흡입에 따른 조음기관의 특성이 변화되는 것을 측정하기 위해 음성분석학적 요소의 적용을 통한 실험을 수행하였다. 헬륨가스는 기존에 잠수부가 사용하던 질소가스가 인체에 치명적인 공기 색전증을 유발하게 되면서 이를 극복하기 위한 대체 호흡용 가스로 사용되고 있다. 그러나, 헬륨가스는 명료도가 낮은 squeaky voice를 유발하기 때문에 잠수부들의 비정상적인 음성에 대한 해석에 어려움이 많다. 따라서, 헬륨가스가 음성기관에 미치는 영향을 음성분석학적 특성 변화로 측정하기 위해 헬륨가스 흡입 전과 후의 음성을 기반으로 피치 및 스펙트로그램 측정, 분석에 대한 실험을 수행하였다.