• 대한의용생체공학회:의공학회지
• /
• 제31권6호
• /
• pp.417-426
• /
• 2010

We present a speech processing strategy incorporating instantaneous frequency (IF) encoding for the enhancement of melody recognition performance of cochlear implants. For the IF extraction from incoming sound, we propose the use of a Teager energy operator (TEO), which is advantageous for its lower computational load. From time-frequency analysis, we verified that the TEO-based method provides proper IF encoding of input sound, which is crucial for melody recognition. Similar benefit could be obtained also from the use of a Hilbert transform (HT), but much higher computational cost was required. The melody recognition performance of the proposed speech processing strategy was compared with those of a conventional strategy using envelope extraction, and the HT-based IF encoding. Hearing tests on normal subjects were performed using acoustic simulation and a musical contour identification task. Insignificant difference in melody recognition performance was observed between the TEO-based and HT-based IF encodings, and both were superior to the conventional strategy. However, the TEO-based strategy was advantageous considering that it was approximately 35% faster than the HT-based strategy.

• ETRI Journal
• /
• 제32권3호
• /
• pp.395-405
• /
• 2010

A novel multiclassifier system (MCS) strategy is proposed and applied to a text-dependent speaker verification task. The presented scheme optimizes the linear combination of classifiers on an on-line basis. In contrast to ordinary MCS approaches, neither a priori distributions nor pre-tuned parameters are required. The idea is to improve the most accurate classifier by making use of the incremental information provided by the second classifier. The on-line multiclassifier optimization approach is applicable to any pattern recognition problem. The proposed method needs neither a priori distributions nor pre-estimated weights, and does not make use of any consideration about training/testing matching conditions. Results with Yoho database show that the presented approach can lead to reductions in equal error rate as high as 28%, when compared with the most accurate classifier, and 11% against a standard method for the optimization of linear combination of classifiers.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.42-47
• /
• 1994

A pitch detector is an essential component in a variety of speech processing systems. Besides providing valuable insights into the nature of the exciation source for speech production, the pitch contour of an utterance is useful for recognizing speakers, aids-to-the handicapped, and is required in almost all speech analysis-synthesis system. Because of the importance of the pitch detection, a wide variety algorithms for pitch detection have been proposed in speech procesing literature. Thus, in this paper we discuss th evarious type of pitch detection algorithms which have been proposed until now. Then we provide th eperformance measurements for seven pitch detection algorithms.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1992년도 학술논문발표회 논문집 제11권 1호
• /
• pp.49-53
• /
• 1992

In many applications such as speech analysis, speech coding, speech recognition, etc., the voiced-unvoiced decision should be performed correctly for efficient processing. One of the parameters which are used for voice-unvoiced decision is zero-crossing. But the information of higher formants have not represented as the zero-crossing rate for higher formants of speech signals.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.603-606
• /
• 1998

In a large number of words and the continued speech recognition system using a phoneme as teh recognition unit, it is necessary to segment processing. In this paper, a normalized AMDF new method. The suggested parameter represents a degree of sharpness at valley point. This method can detect the speech segment between the steady state and transient region to the continued speech without a prior information of speech signal.

• The Journal of the Acoustical Society of Korea
• /
• 제23권3E호
• /
• pp.85-90
• /
• 2004

This paper presents two kinds of new approaches, one of which is concerned with recognition of emotional speech such as anger, happiness, normal, sadness, or surprise. The other is concerned with emotion recognition in speech. For the proposed speech recognition system handling human speech with emotional states, total nine kinds of prosodic features were first extracted and then given to prosodic identifier. In evaluation, the recognition results on emotional speech showed that the rates using proposed method increased more greatly than the existing speech recognizer. For recognition of emotion, on the other hands, four kinds of prosodic parameters such as pitch, energy, and their derivatives were proposed, that were then trained by discrete duration continuous hidden Markov models(DDCHMM) for recognition. In this approach, the emotional models were adapted by specific speaker's speech, using maximum a posteriori(MAP) estimation. In evaluation, the recognition results on emotional states showed that the rates on the vocal emotions gradually increased with an increase of adaptation sample number.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 추계 학술대회 발표논문집
• /
• pp.13-16
• /
• 2005

As language learning that utilizes speech and information processing technology is getting popular. Speech Information Technology & Promotion Center(SiTEC) has created and is distributing speech corpora for STiLL in order to support basic research and development of products. We will introduce the corpus for Korean and those for English which we have created and are distributing.

• 한국정보통신학회논문지
• /
• 제20권9호
• /
• pp.1673-1678
• /
• 2016

음성인식처리 분야에서 배경잡음으로 인하여 음성입력이 배경잡음으로 잘못 판단되는 원인이 되어 음성인식율의 저하를 초래한다. 이러한 종류의 잡음대책은 단순하지 않으므로 보다 고도한 잡음처리기술이 필요하게 된다. 따라서 본 논문에서는 잡음환경 중에서 정상적인 배경잡음 혹은 비정상적인 배경잡음과 지속 시간이 짧은 음성을 구별하는 알고리즘에 대하여 기술한다. 본 알고리즘은 다른 종류의 잡음과 음성을 구별하는 중요한 수단으로서 개량된 음성의 특징파리미터를 사용한다. 다음으로 다층퍼셉트론 네트워크에 의하여 잡음의 종류를 추정하는 알고리즘에 대해서 기술한다. 본 실험에서는 잡음과 음성이 구별이 가능하도록 실험적으로 확인하였다.

• 한국정보통신학회논문지
• /
• 제15권8호
• /
• pp.1665-1674
• /
• 2011

본 논문에서는 유색잡음에 의해 오염된 음성신호의 음성향상 알고리즘을 제안한다. 유색잡음과 음성신호가 서로 상관이 없을 경우 유색잡음은 백색화 변환을 통해 무색잡음으로 변환된다. 이 변환된 신호를 음성신호 향상을 위한 일반화된 부공간 접근법에 적용한다. 전처리 과정에서의 백색화 변환으로 발생되는 음성 스펙트럼 왜곡은 제안한 알고리즘의 후처리를 통해 역 백색화하여 복구한다. 제안한 알고리즘의 성능을 컴퓨터 시뮬레이션으로 확인하였다. 사용한 유색잡음은 자동차 잡음과 멀티 토커 배블 잡음이다. AURORA 및 TIMIT 데이터 베이스에서 취득한 데이터로 실험했을 때 제안하는 방법이 신호대잡음비 및 스펙트럼 왜곡 측면에서 기존 접근법보다 개선됨을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.413-416
• /
• 2002

In this paper, a speech enhancement system using microphone array with adaptive Post-Processing is implemented in real-lime with TMS320C6201 DSP. It consists of delay-and-sum beamformer and adaptive post-processing filters with NLMS (Normalized Least Mean Square) algorithm. THS1206 ADC is used for collection of 4-channel microphone signals. Sizes of program memory, data ROM and data RAM of the implemented system are 15,744, 748 and 47,540 bytes, respectively. Finally 21.839${\times}$106 clocks per second is required for real-time operation.