• ETRI Journal
• /
• v.33 no.5
• /
• pp.741-751
• /
• 2011

This paper focuses on online speaker tracking for telephone conversations and broadcast news. Since the online applicability imposes some limitations on the tracking strategy, such as data insufficiency, a reliable approach should be applied to compensate for this shortage. In this framework, a set of reference speaker models are used as side information to facilitate online tracking. To improve the indexing accuracy, adaptation approaches in eigenvoice decomposition space are proposed in this paper. We believe that the eigenvoice adaptation techniques would help to embed the speaker space in the models and hence enrich the generality of the selected speaker models. Also, an index structure of the reference models is proposed to speed up the search in the model space. The proposed framework is evaluated on 2002 Rich Transcription Broadcast News and Conversational Telephone Speech corpus as well as a synthetic dataset. The indexing errors of the proposed framework on telephone conversations, broadcast news, and synthetic dataset are 8.77%, 9.36%, and 12.4%, respectively. Using the index tree structure approach, the run time of the proposed framework is improved by 22%.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.151-154
• /
• 2002

본 논문에서는 음성 데이터에서 동일한 화자의 음성 구간을 찾아내는 화자 인덱싱(Speaker Indexing) 기술 중 사전 화자 모델링 과정을 통한 인덱싱 방법을 제안하고 실험하였다. 제안한 인덱싱 방법은 문장 독립(Text Independent) 화자 식별(Speaker Identification)에 사용할 수 있는 모음(Vowel)에 대해 특징 파라미터를 추출하고, 이를 바탕으로 화자별 모델을 구성하였다. 인덱싱은 음성 구간에서 모음의 위치를 검출하고, 구성한 화자 모델과의 거리 계산을 통하여 가장 가까운 모델을 식별된 결과로 한다. 그리고 식별된 결과는 화자 구간 변화와 음성 데이터의 특성을 바탕으로 필터링 과정을 거쳐 최종적인 인덱싱 결과를 얻는다. 화자 인덱싱 실험 대상으로 방송 뉴스를 녹음하여 10명의 화자 모델을 구성하였고, 인덱싱 실험을 수행한 결과 $91.8\%$의 화자 인덱싱 성능을 얻었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.122-127
• /
• 1998

In this paper, we focus on the information retrieval of human individuals who are recorded on the video database. Our purpose is to index persons by their faces or voice and to retrieve their existing time sections on the video data. The database system can track as well as extract a face or voice of a certain person and construct a model of the individual person in self-organization mode. If he appears again at different time, the system can put the mark of the same person to the associated frames. In this way, the same person can be retrieved even if the system does not know his exact name. As the face and speaker modeling, a subspace method is employed to improve the indexing accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.5
• /
• pp.244-251
• /
• 2008

In this research, we propose an unsupervised debate indexing method using audio and visual information. The proposed method combines clustering results of speech by BIC and visual by distance function. The combination of audio-visual information reduces the problem of individual use of speech and visual information. Also, an effective content based analysis is possible. We have performed various experiments to evaluate the proposed method according to use of audio-visual information for five types of debate data. From experimental results, we found that the effect of audio-visual integration outperforms individual use of speech and visual information for debate indexing.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.92-96
• /
• 2004

The researches of the emotions are currently great interest in speech processing as well as in human-machine interaction domain. In the recent years, more and more of researches relating to emotion synthesis or emotion recognition are developed for the different purposes. Each approach uses its methods and its various parameters measured on the speech signal. In this paper, we proposed using a short-time parameter: MFCC coefficients (Mel­Frequency Cepstrum Coefficients) and a simple but efficient classifying method: Vector Quantification (VQ) for speaker-dependent emotion recognition. Many other features: energy, pitch, zero crossing, phonetic rate, LPC... and their derivatives are also tested and combined with MFCC coefficients in order to find the best combination. The other models: GMM and HMM (Discrete and Continuous Hidden Markov Model) are studied as well in the hope that the usage of continuous distribution and the temporal behaviour of this set of features will improve the quality of emotion recognition. The maximum accuracy recognizing five different emotions exceeds $88\%$ by using only MFCC coefficients with VQ model. This is a simple but efficient approach, the result is even much better than those obtained with the same database in human evaluation by listening and judging without returning permission nor comparison between sentences [8]; And this result is positively comparable with the other approaches.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.5
• /
• pp.207-213
• /
• 2007

In this research, we propose an efficient Speech/Music discrimination method that uses spectrum analysis and neural network. The proposed method extracts the duration feature parameter(MSDF) from a spectral peak track by analyzing the spectrum, and it was used as a feature for Speech/Music discriminator combined with the MFSC. The neural network was used as a Speech/Music discriminator, and we have reformed various experiments to evaluate the proposed method according to the training pattern selection, size and neural network architecture. From the results of Speech/Music discrimination, we found performance improvement and stability according to the training pattern selection and model composition in comparison to previous method. The MSDF and MFSC are used as a feature parameter which is over 50 seconds of training pattern, a discrimination rate of 94.97% for speech and 92.38% for music. Finally, we have achieved performance improvement 1.25% for speech and 1.69% for music compares to the use of MFSC.