• 음성과학
• /
• 제11권2호
• /
• pp.51-67
• /
• 2004

The objective of this study was to investigate the effects in auditory performance and vocal development of Onomatopoeia and Mimetic Word Productive Training Program in prelingually deafened children with cochlear implantation. The effects were measured with Lip-profile (Listening progress profile: LiP), the number of utterances, vocal developmental level and phonetic inventory. Subjects were four children with cochlear implants who were able to detect speech sounds and environmental sounds. The Onomatopoeia and Mimetic word Productive Training Program was made up of 3 steps with 24 Onomatopoeia and Mimetic words. This study was pre and post design. The results of the study were as follows: First, after Onomatopoeia and Mimetic word Productive Training Program was treated, LiP score was significantly higher. Second, after this program was treated, the number of utterances and emergence of both canonical and postcanonical utterances were increased. Emergence of vowel and consonant Features were increased and diversified. In conclusion, Onomatopoeia and Mimetic Word Productive Training Program appeared to facilitate efficient auditory performance and vocal development.

• 대한음성학회지:말소리
• /
• 제58호
• /
• pp.83-99
• /
• 2006

One key factor that hinders the widespread deployment of speaker identification technologies is the requirement of long enrollment utterances to guarantee low error rate during identification. To gain user acceptance of speaker identification technologies, adaptation algorithms that can enroll speakers with short utterances are highly essential. To this end, this paper applies MLLR speaker adaptation for speaker enrollment and compares its performance against other speaker modeling techniques: GMMs and HMM. Also, to speed up the computational procedure of identification, we apply speaker clustering method which uses principal component analysis (PCA) and weighted Euclidean distance as distance measurement. Experimental results show that MLLR adapted modeling method is most effective for short enrollment utterances and that the GMMs performs better when long utterances are available.

• 한국음향학회지
• /
• 제37권6호
• /
• pp.483-488
• /
• 2018

원거리 발성은 화자 인증 시스템의 성능을 하락시키는 주요 요인으로 알려져 있다. 본 논문에서는 교사 학생 학습을 이용하여 원거리 발성에 의한 화자 인증 시스템의 성능 하락을 보상하는 기법을 제안한다. 교사 학생 학습은 미리 학습된 교사 심층신경망의 출력과 학생 신경망의 출력이 같아지도록 학생 신경망을 학습하는 기법이다. 여기서 교사 신경망에는 근거리 발성을, 학생 신경망에는 원거리 발성을 입력한 뒤, 두 신경망의 출력을 동일하게 만드는 과정을 통해 원거리 발성을 보상할 수 있을 것이라고 기대하였다. 하지만 원거리 발성을 보상하는 과정에서, 근거리 발성에 대한 인식률이 저하되는 현상을 실험적으로 발견하였다. 위와 같은 현상을 예방하기 위해 본 논문에서는 교사 심층신경망을 학생 심층신경망의 초깃값으로 사용하는 기법과 학생 심층신경망을 근거리 발성에 대해서도 학습하는 기법을 제안하였다. 모든 실험은 원 음성을 입력 받는 심층신경망을 활용해 수행하였다. 동일한 발성을 각각 4 채널로 근거리와 원거리에서 자체적으로 수집한 문장 종속 데이터셋을 활용하였다. 동일 오류율을 기준으로 근거리 / 원거리 발성에 대한 화자 인증 성능을 평가한 결과 교사 학생 학습을 사용하지 않을 경우 2.55 % / 2.8 %, 기존의 교사 학생 학습을 사용할 경우 9.75 % / 1.8 %, 제안한 기법들을 적용한 경우 2.5 % / 2.7 %의 오류율을 확인하였다.

• 말소리와 음성과학
• /
• 제4권2호
• /
• pp.79-86
• /
• 2012

In this paper, we propose a novel approach to improve histogram equalization for speaker identification. Our method collects all speech features of UBM training data to make a reference distribution. The ranks of the feature vectors are calculated in the sorted list of the collection of the UBM training data and the test data. We use the ranks to perform order-based histogram equalization. The proposed method improves the accuracy of the speaker recognition system with short utterances. We use four kinds of speech databases to evaluate the proposed speaker recognition system and compare the system with cepstral mean normalization (CMN), mean and variance normalization (MVN), and histogram equalization (HEQ). Our system reduced the relative error rate by 33.3% from the baseline system.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권3호
• /
• pp.179-186
• /
• 2009

본 논문에서는 학습이 가능한 특정화자의 발화음성이 있는 경우, 잡음과 반향이 있는 실 환경에서의 스테레오 마이크로폰을 이용한 특정화자 음성복원 알고리즘을 제안한다. 이를 위해 반향이 있는 환경에서 음원들을 분리하는 다중경로 암묵음원분리(convolutive blind source separation, CBSS)와 이의 후처리 방법을 결합함으로써, 잡음이 섞인 다중경로 신호로부터 잡음과 반향을 제거하고 특정화자의 음성만을 복원하는 시스템을 제시한다. 즉, 비음수 행렬분해(non-negative matrix factorization, NMF) 방법을 이용하여 특정화자의 학습음성으로부터 주파수 특성을 보존하는 기저벡터들을 학습하고, 이 기저벡터들에 기반 한 두 단계의 후처리 기법들을 제안한다. 먼저 본 시스템의 중간단계인 CBSS가 다중경로 신호를 입력받아 독립음원들을(두 채널) 출력하고, 이 두 채널 중 특정화자의 음성에 보다 가까운 채널을 자동적으로 선택한다(채널선택 단계). 이후 앞서 선택된 채널의 신호에 남아있는 잡음과 다른 방해음원(interference source)을 제거하여 특정화자의 음성만을 복원, 최종적으로 잡음과 반향이 제거된 특정화자의 음성을 복원한다(복원 단계). 이 두 후처리 단계 모두 특정화자 음성으로부터 학습한 기저벡터들을 이용하여 동작하므로 특정화자의 음성이 가지는 고유의 주파수 특성 정보를 효율적으로 음성복원에 이용 할 수 있다. 이로써 본 논문은 CBSS에 음원의 사전정보를 결합하는 방법을 제시하고 기존의 CBSS의 분리 결과를 향상시키는 동시에 특정화자만의 음성을 복원하는 시스템을 제안한다. 실험을 통하여 본 제안 방법이 잡음과 반향 환경에서 특정화자의 음성을 성공적으로 복원함을 확인할 수 있다.

• 음성과학
• /
• 제11권4호
• /
• pp.43-52
• /
• 2004

Model parameters in HMM based speech recognition systems are normally estimated using Maximum Likelihood Estimation(MLE). The MLE method is based mainly on the principle of statistical data fitting in terms of increasing the HMM likelihood. The optimality of this training criterion is conditioned on the availability of infinite amount of training data and the correct choice of model. However, in practice, neither of these conditions is satisfied. In this paper, we propose a training algorithm, MCE(Minimum Classification Error), to improve the performance of a speech recognizer detecting mispronunciation of a foreign language. During the conventional MLE(Maximum Likelihood Estimation) training, the model parameters are adjusted to increase the likelihood of the word strings corresponding to the training utterances without taking account of the probability of other possible word strings. In contrast to MLE, the MCE training scheme takes account of possible competing word hypotheses and tries to reduce the probability of incorrect hypotheses. The discriminant training method using MCE shows better recognition results than the MLE method does.

• ETRI Journal
• /
• 제28권6호
• /
• pp.807-810
• /
• 2006

This letter presents a prediction model for sentence-final intonations for Korean conversational-style text-to-speech systems in which we introduce the linguistic feature of 'modality' as a new parameter. Based on their function and meaning, we classify tonal forms in speech data into tone types meaningful for speech synthesis and use the result of this classification to build our prediction model using a tree structured classification algorithm. In order to show that modality is more effective for the prediction model than features such as sentence type or speech act, an experiment is performed on a test set of 970 utterances with a training set of 3,883 utterances. The results show that modality makes a higher contribution to the determination of sentence-final intonation than sentence type or speech act, and that prediction accuracy improves up to 25% when the feature of modality is introduced.

• 한국음향학회지
• /
• 제39권1호
• /
• pp.64-68
• /
• 2020

가우스 혼합 모델-은닉 마코프 모델(Gaussian Mixture Model-Hidden Markov Model, GMM-HMM)을 이용하는 전통적인 음성인식 시스템에서는, 극점 필터링 기반의 켑스트럼 특징 정규화 방식이 잡음 환경에서 짧은 발화의 인식 성능을 향상시키는데 효과적이었다. 본 논문에서는 심층신경망(Deep Neural Network, DNN)을 이용하는 최신의 음성인식 시스템에서도 이 방식의 유용성이 있는지 검토한다. AURORA 2 DB에 대한 실험 결과, 특히 훈련 및 테스트 환경 사이의 불일치가 클 때에, 극점 필터링 기반의 켑스트럼 평균 분산 정규화 방식이 극점 필터링을 사용하지 않는 방식에 비해 매우 짧은 발화의 인식 성능을 개선시킴을 보여 준다.

• 말소리와 음성과학
• /
• 제15권2호
• /
• pp.53-59
• /
• 2023

Detection of children with autism spectrum disorder (ASD) based on speech has relied on predefined feature sets due to their ease of use and the capabilities of speech analysis. However, clinical impressions may not be adequately captured due to the broad range and the large number of features included. This paper demonstrates that the knowledge-driven speech features (KDSFs) specifically tailored to the speech traits of ASD are more effective and efficient for detecting speech of ASD children from that of children with typical development (TD) than a predefined feature set, extended Geneva Minimalistic Acoustic Standard Parameter Set (eGeMAPS). The KDSFs encompass various speech characteristics related to frequency, voice quality, speech rate, and spectral features, that have been identified as corresponding to certain of their distinctive attributes of them. The speech dataset used for the experiments consists of 63 ASD children and 9 TD children. To alleviate the imbalance in the number of training utterances, a data augmentation technique was applied to TD children's utterances. The support vector machine (SVM) classifier trained with the KDSFs achieved an accuracy of 91.25%, surpassing the 88.08% obtained using the predefined set. This result underscores the importance of incorporating domain knowledge in the development of speech technologies for individuals with disorders.

• 대한음성학회지:말소리
• /
• 제68권
• /
• pp.49-63
• /
• 2008

This paper describes the development and assessment of a hidden Markov model (HMM) based Tagalog speech synthesis system, where Tagalog is the most widely spoken indigenous language of the Philippines. Several aspects of the design process are discussed here. In order to build the synthesizer a speech database is recorded and phonetically segmented. The constructed speech corpus contains approximately 89 minutes of Tagalog speech organized in 596 spoken utterances. Furthermore, contextual information is determined. The quality of the synthesized speech is assessed by subjective tests employing 25 native Tagalog speakers as respondents. Experimental results show that the new system is able to obtain a 3.29 MOS which indicates that the developed system is able to produce highly intelligible neutral Tagalog speech with stable quality even when a small amount of speech data is used for HMM training.