• 융합신호처리학회논문지
• /
• 제15권2호
• /
• pp.37-41
• /
• 2014

The vector Taylor series (VTS) based method usually employs clean speech Hidden Markov Models (HMMs) when compensating speech feature vectors or adapting the parameters of trained HMMs. It is well-known that noisy speech HMMs trained by the Multi-condition TRaining (MTR) and the Multi-Model-based Speech Recognition framework (MMSR) method perform better than the clean speech HMM in noisy speech recognition. In this paper, we propose a method to use the noise-adapted HMMs in the VTS-based speech feature compensation method. We derived a novel mathematical relation between the train and the test noisy speech feature vector in the log-spectrum domain and the VTS is used to estimate the statistics of the test noisy speech. An iterative EM algorithm is used to estimate train noisy speech from the test noisy speech along with noise parameters. The proposed method was applied to the noise-adapted HMMs trained by the MTR and MMSR and could reduce the relative word error rate significantly in the noisy speech recognition experiments on the Aurora 2 database.

• 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.

• 음성과학
• /
• 제13권4호
• /
• pp.177-186
• /
• 2006

In an effort to enhance the quality of feature vector classification and thereby reduce the recognition error rate of the speaker-independent speech recognition, we employ the Mahalanobis distance in the calculation of the similarity measure between feature vectors. It is assumed that the metric matrix of the Mahalanobis distance be diagonal for the sake of cost reduction in memory and time of calculation. We propose that the diagonal elements be given in terms of the variations of the feature vector components. Geometrically, this prescription tends to redistribute the set of data in the shape of a hypersphere in the feature vector space. The idea is applied to the speech recognition by hidden Markov model with fuzzy vector quantization. The result shows that the recognition is improved by an appropriate choice of the relevant adjustable parameter. The Viterbi score difference of the two winners in the recognition test shows that the general behavior is in accord with that of the recognition error rate.

• 한국정보통신학회논문지
• /
• 제20권3호
• /
• pp.471-476
• /
• 2016

본 논문에서는 음성 특성 지표를 이용한 음성 인식 성능 예측 실험의 내용을 소개한다. 선행 실험에서 효과적인 음성 인식 성능 예측을 위해 대표적인 음성 인식 성능 지표인 단어 오인식률과 상관도가 높은 여러 가지 특성 지표들을 조합하여 새로운 성능 지표를 제안하였다. 제안한 지표는 각 음성 특성 지표를 단독으로 사용할 때 보다 단어 오인식률과 높은 상관도를 나타내 음성 인식 성능을 예측하는데 효과적임을 보였다. 본 실험에서는 이 결과를 근거하여 조합에 사용된 음성 특성 지표를 채택하여 4차원 특징 벡터를 생성하고 GMM 기반의 음성 인식 성능 예측기를 구축한다. 가우시안 요소를 증가시키며 실험한 결과 제안된 시스템은 babble 잡음, 자동차 잡음에서 모두 SNR이 낮을수록 단어 오인식률을 높은 확률로 예측함을 확인하였다.

• 한국산학기술학회논문지
• /
• 제12권12호
• /
• pp.5843-5848
• /
• 2011

EVRC에서는 채널 스펙트럼의 효율을 높이고 시스템의 소비 전력을 줄이기 위하여, 통화시간 중에서 사용자가 말을 할 때만 음성신호를 압축하여 전달하고, 말을 하지 않을 때는 음성신호를 전달하지 않는다. 또한, EVRC에서는 음성 프레임을 1, 1/2, 1/8의 세 가지 전송률로 구분하여 다르게 처리 하고 있으며, 예를 들어, 1/8 전송률은 입력 신호가 묵음구간인 것을 의미한다. 본 연구에서는 LSP 파라미터의 분포특성을 이용한 유성음 구간, 무성음 구간, 묵음 구간을 구분하는 방법을 사용하여, 유성음인 경우에 대해 1 rate으로 부호화하고, 무성음 구간의 경우는 1/2 rate, 묵음의 경우에는 1/8 rate으로 전송하는 방법에 대하여 제안하였다. 즉, EVRC에서 full rate으로 보내는 부분에 대해서는 기존의 방식을 그대로 적용하며, half rate은 유성음, 무성음을 구분하여 유성음일 경우 full rate으로 바꾸어 전송하였고, 묵음에 대해서는 EVRC 기본 rate을 적용하였다. 실험과정에서는, SNR, ASDM, 전송률을 측정하였으며, 제안한 알고리즘을 사용하는 경우 EVRC에 비해 음성품질이 향상됨을 증명하였다.

• 전기학회논문지
• /
• 제62권4호
• /
• pp.562-565
• /
• 2013

A new variable rate speech coding technique is proposed. The method is based on the observation that the speech signal approximately looks linear for a very short period of time. The information transmitted is the location and data value of inflection points. If the distance between the inflection points is large, the mid point location and its data value are also delivered. Thus, the encoder transmits both the location and the data value for the inflection samples, but the location only for the non-inflection points. The location information is expressed using one bit for each sample, 0 for non-inflection and 1 for inflection point. At the receiver, using the interpolation, the decoder estimates the untransmitted sample values for non-inflection locations from the received sample values for the inflection samples. With 50 % of computational cost of the existing CVSD delta modulation, the proposed method is expected to achieve the data rate of 36 to 38 kbps and the SNR of 10 to 13 dB.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.827-830
• /
• 2000

본 논문에서는 ETSI와 3GPP에서 차세대 이동통신 IMT-2000 서비스의 음성부호화기의 표준안으로 채택한 AMR(Adaptive Multi-Rate)에 대해 알고리즘을 분석하고 Texas Instrument 사에서 제공한 C 컴파일러와 어셈블리 언어를 이용하여 최적화 과정을 수행하였다. 인코더 약 28.2MIPS, 디코더 5.5MIPS로 40MIPS의 사양을 가지는 TMS320C542 보드의 82%를 사용하여 실시간 구현을 하였다. 또한 DSP보드상에서 구현한 결과가 ETSI에서 제공한 ANSI C 소스 프로그램의 결과와 일치됨을 확인하였으며, 마이크 입력과 증폭기를 이용한 스피커 출력의 시스템을 구성하여 지연과 왜곡이 없음을 확인하였다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.149-151
• /
• 2007

This study was designed to investigate fast ab/adduction rate of articulation valves in normal adults. The measurement of fast ab/aduction rate has traditionally been used for assessment, diagnosis and therapy in patients who suffered from dysarthria, functional articulation disorders or apraxia of speech. Fast ab/adduction rate shows the documented structural and physiological changes in the central nervous system and the peripheral components of oral and speech production mechanism. Fast ab/adduction rates were obtained from 20 normal subjects by producing the repetition of vocal function (/ihi/), tongue function (/t${\wedge}$/), velopharyngeal function (/m/), and labial function (/p${\wedge}$/). The Aerophone II was used for data recording. The results of finding as follows: average fast ab/adduction rates were vocal function(6.21cps), tongue function(7.42cps), velopharyngeal function(5.23cps), labial function (6.93cps). The results of this study are guidelines of normal diadochokinetic rates. In addition, they can indicate the severity of diseases and evaluation of treatment.

• 말소리와 음성과학
• /
• 제4권4호
• /
• pp.117-127
• /
• 2012

This research reports the prosodic characteristics (including articulation speech rate, pause characteristics, duration) of children with cochlear implants with reference to those of children with normal hearing. Subjects are 8-to 10-year-old children, balancing each number of gender as 24. Dialogue speech data are comprised of four types of sentence patterns. Results show that 1) there's a statistically meaningful difference on articulation speech rate between the two groups. 2) On pauses, they are not observed in exclamatory and declarative sentences in normal children. While imperative sentences show no statistical difference on the number of pauses between the two groups, interrogative sentences do. 3) Declarative, exclamatory, and interrogative sentences reveal statistical difference between the two groups in terms of the sentence's final two-syllable word duration, showing no difference on imperative sentences. 4) When it comes to the RFP (duration ratio of sentence final syllable to penultimate syllable), we no statistically meaningful difference between the two groups in all types of sentences exists. 5) Lastly, RWS (the ratio of sentence final two syllable word duration to that of whole sentence duration) shows statistical difference between two groups in imperative sentences, but not in all the rest types.

• The Journal of the Acoustical Society of Korea
• /
• 제22권3E호
• /
• pp.124-132
• /
• 2003

We propose a new method for speech/non-speech classifiers based on concepts of the adaptive boosting (AdaBoost) algorithm in order to detect speech for robust speech recognition. The method uses a combination of simple base classifiers through the AdaBoost algorithm and a set of optimized speech features combined with spectral subtraction. The key benefits of this method are the simple implementation, low computational complexity and the avoidance of the over-fitting problem. We checked the validity of the method by comparing its performance with the speech/non-speech classifier used in a standard voice activity detector. For speech recognition purpose, additional performance improvements were achieved by the adoption of new features including speech band energies and MFCC-based spectral distortion. For the same false alarm rate, the method reduced 20-50% of miss errors.