• 한국통신학회논문지
• /
• 제33권3C호
• /
• pp.234-239
• /
• 2008

For the efficient coding and transmission, the speech signal can be classified into three distinctive classes: voiced, unvoiced, and transition classes. At low bit rate coding below 4 kbit/s, conventional sinusoidal transform coders synthesize speech of high quality for the purely voiced and unvoiced classes, whereas not for the transition class. The transition class including plosive sound and abrupt voiced-onset has the lack of periodicity, thus it is often classified and synthesized as the unvoiced class. In this paper, the efficient algorithm for the transition class detection is proposed, which demonstrates superior detection performance not only for clean speech but for noisy speech. For the detected transition frame, phase information is transmitted instead of magnitude information for speech synthesis. From the listening test, it was shown that the proposed algorithm produces better speech quality than the conventional one.

• 말소리와 음성과학
• /
• 제1권3호
• /
• pp.95-102
• /
• 2009

In this paper, an efficient target speech detection algorithm is proposed for the performance improvement of multi-input speech enhancement. Using the normalized cross correlation value between two selected channels, the proposed algorithm estimates the probabilistic distribution function of the value from the pure noise interval. Then, log-likelihoods are calculated with the function and the normalized cross correlation value to detect the target speech interval precisely. The detection results are applied to the generalized sidelobe canceller-based algorithm. Experimental results show that the proposed algorithm significantly improves the speech recognition performance and the signal-to-noise ratios.

• 대한음성학회지:말소리
• /
• 제49호
• /
• pp.123-134
• /
• 2004

An automatic pronunciation correction system provides learners with correction guidelines for each mispronunciation. In this paper we propose an HMM based speech recognizer which automatically classifies pronunciation errors when Koreans speak Japanese. We also propose two pronunciation networks for automatic detection of mispronunciation. In this paper, we evaluated performances of the networks by computing the correlation between the human ratings and the machine scores obtained from the speech recognizer.

• 전자공학회논문지CI
• /
• 제48권1호
• /
• pp.101-107
• /
• 2011

음성인식의 실용화에 가장 저해되는 요소는 배경잡음과 채널에 의한 왜곡이다. 일반적으로 잡음은 음성인식 시스템의 성능을 저하시키고 이로 인해 사용 장소의 제약을 많이 받고 있다. DSR(Distributed Speech Recognition) 기반의 음성인식 역시 이 같은 문제로 성능 향상에 어려움을 겪고 있다. 이 논문은 잡음환경에서 DSR기반의 음성인식률 향상을 위해 정확한 음성구간을 검출하고, 잡음을 제거하여 잡음에 강인한 특징추출을 하도록 설계하였다. 제안된 방법은 엔트로피와 음성의 하모닉을 이용해 음성구간을 검출하며 멀티밴드 스펙트럼 차감법을 이용하여 잡음을 제거한다. 음성의 스펙트럼 에너지에 대한 엔트로피를 사용하여 음성검출을 하게 되면 비교적 높은 SNR 환경 (SNR 15dB) 에서는 성능이 우수하나 잡음환경의 변화에 따라 음성과 비음성의 문턱 값이 변화하여 낮은 SNR환경(SNR 0dB)에시는 정확한 음성 검출이 어렵다. 이 논문은 낮은 SNR 환경(0dB)에서도 정확한 음성을 검출할 수 있도록 음성의 스펙트럴 엔트로피와 하모닉 성분을 이용하였으며 정확한 음성 구간 검출에 따라 잡음을 제거하여 잡음에 강인한 특정을 추출하도록 하였다. 실험결과 잡음환경에 따른 인식조건에서 개선된 인식성능을 보였다.

• 방송공학회논문지
• /
• 제22권2호
• /
• pp.253-256
• /
• 2017

본 논문에서는 기계학습 기반의 분류 방법을 이용하여 장애 음성을 검출하고자 한다. 음성 장애 중 마비말 장애는 뇌성마비, 파킨슨 질환, 뇌졸중 등 주로 뇌질환에 의해 발생하는 것으로 알려져 있다. 이러한 장애 음성을 검출함으로써 뇌졸중 등의 급성 뇌질환 발생에 대한 조기 처치가 가능하다. 장애 음성 검출은 입력 음성에 대한 특징벡터 추출과 기계학습을 이용한 분류과정을 통해 이루어질 수 있다. 실험을 위해서 장애 음성 DB인 TORGO 데이터를 사용하였으며, 10가지 기계학습 알고리즘과 다양한 특징벡터 스케일링 방법에 대해 장애 음성 검출 성능을 평가하였다.

• 말소리와 음성과학
• /
• 제1권2호
• /
• pp.15-22
• /
• 2009

Prominence of speech, which is often called 'accent,' affects the fluency of speaking American English greatly. In this paper, we present an accurate prominence detection method that can be utilized in computer-aided language learning (CALL) systems. We employed pitch movement, overall syllable energy, 300-2200 Hz band energy, syllable duration, and spectral and temporal correlation as features to model the prominence of speech. After the features for vowel syllables of speech were extracted, prominent syllables were classified by SVM (Support Vector Machine). To further improve accuracy, the differences in characteristics of neighboring syllables were added as additional features. We also applied a speech recognizer to extract more precise syllable boundaries. The performance of our prominence detector was measured based on the Intonational Variation in English (IViE) speech corpus. We obtained 84.9% accuracy which is about 10% higher than previous research.

• 방송공학회논문지
• /
• 제22권5호
• /
• pp.632-642
• /
• 2017

본 논문에서는 미디어 오디오의 음향 특성 및 문맥 정보를 활용한 DNN 기반 음성 검출 시스템을 제안한다. 미디어 오디오 내에 포함되어 있는 음성과 비음성을 구분하기 위한 음성 검출 기법은 효과적인 음성 처리를 위해 필수적인 전처리 기술이지만 미디어 오디오 신호에는 다양한 형태의 음원이 복합적으로 포함되어 있으므로 기존의 신호처리 기법으로는 높은 성능을 얻기에는 어려움이 있었다. 제안하는 기술은 미디어 오디오의 고조파와 퍼커시브 성분을 분리하고, 오디오 콘텐츠에 포함된 문맥 정보를 반영하여 DNN 입력 벡터를 구성함으로써 음성 검출 성능을 개선할 수 있다. 제안하는 시스템의 성능을 검증하기 위하여 20시간 이상 분량의 드라마를 활용하여 음성 검출용 데이터 세트를 제작하였으며 범용으로 공개된 8시간 분량의 헐리우드 영화 데이터 세트를 추가로 확보하여 실험에 활용하였다. 실험에서는 두 데이터 세트에 대한 교차 검증을 통하여 제안하는 시스템이 기존 방법에 비해 우수한 성능을 보임을 확인하였다.

• 말소리와 음성과학
• /
• 제2권3호
• /
• pp.141-148
• /
• 2010

In this paper, voice activity detection (VAD) for dual-channel noisy speech recognition is proposed in which spatial cues are employed. In the proposed method, a probability model for speech presence/absence is constructed using spatial cues obtained from dual-channel input signal, and a speech activity interval is detected through this probability model. In particular, spatial cues are composed of interaural time differences and interaural level differences of dual-channel speech signals, and the probability model for speech presence/absence is based on a Gaussian kernel density. In order to evaluate the performance of the proposed VAD method, speech recognition is performed for speech segments that only include speech intervals detected by the proposed VAD method. The performance of the proposed method is compared with those of several methods such as an SNR-based method, a direction of arrival (DOA) based method, and a phase vector based method. It is shown from the speech recognition experiments that the proposed method outperforms conventional methods by providing relative word error rates reductions of 11.68%, 41.92%, and 10.15% compared with SNR-based, DOA-based, and phase vector based method, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1291-1295
• /
• 2004

This paper proposed a new approach for endpoint detection of isolated speech, which proves to significantly improve the endpoint detection performance. The proposed algorithm relies on the root mean square energy (rms energy), zero crossing rate and spectral characteristics of the speech signal where the Euclidean distance measure is adopted using cepstral coefficients to accurately detect the endpoint of isolated speech. The algorithm offers better performance than traditional energy-based algorithm. The vocabulary for the experiment includes English digit from one to nine. These experimental results were conducted by 360 utterances from a male speaker. Experimental results show that the accuracy of the algorithm is quite acceptable. Moreover, the computation overload of this algorithm is low since the cepstral coefficients parameters will be used in feature extraction later of speech recognition procedure.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.381-384
• /
• 2002

In speech signal processing, it Is very important to detect the pitch exactly in speech recognition, synthesis and analysis. but, it is very difficult to pitch detection from speech signal because of formant and transition amplitude affect. therefore, in this paper, we proposed a pitch detection using the spectrum flattening techniques. Spectrum flattening is to eliminate the formant and transition amplitude affect. In time domain, positive center clipping is process in order to emphasize pitch period with a glottal component of removed vocal tract characteristic. And rough formant envelope is computed through peak-fitting spectrum of original speech signal in frequency domain. As a results, well get the flattened harmonics waveform with the algebra difference between spectrum of original speech signal and smoothed formant envelope. After all, we obtain residual signal which is removed vocal tract element The performance was compared with LPC and Cepstrum, ACF 0wing to this algorithm, we have obtained the pitch information improved the accuracy of pitch detection and gross error rate is reduced in voice speech region and in transition region of changing the phoneme.