• The Journal of the Acoustical Society of Korea
• /
• v.26 no.3E
• /
• pp.74-79
• /
• 2007

In this paper, we report our recent work on a indexing and retrieval system of broadcast news using audio content analysis. Key issues addressed in this work are two major parts of the audio indexing system: anchorperson detection based on audio segmentation, and phone-based spoken document retrieval, developed in the framework of the emerging MPEG-7 standard. Experiments are conducted on a database of Britisch broadcast news videos. We discuss the development of the retrieval system, and the evaluation of each part and the retrieval system.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.87-96
• /
• 2021

The demand for e-learning through video lectures is rapidly increasing due to its diverse advantages over the traditional learning methods. This led to massive volumes of web-based lecture videos. Indexing and retrieval of a lecture video or a lecture video topic has thus proved to be an exceptionally challenging problem. Many techniques listed by literature were either visual or audio based, but not both. Since the effects of both the visual and audio components are equally important for the content-based indexing and retrieval, the current work is focused on both these components. A framework for automatic topic-based indexing and search depending on the innate content of the lecture videos is presented. The text from the slides is extracted using the proposed Merged Bounding Box (MBB) text detector. The audio component text extraction is done using Google Speech Recognition (GSR) technology. This hybrid approach generates the indexing keywords from the merged transcripts of both the video and audio component extractors. The search within the indexed documents is optimized based on the Naïve Bayes (NB) Classification and K-Means Clustering models. This optimized search retrieves results by searching only the relevant document cluster in the predefined categories and not the whole lecture video corpus. The work is carried out on the dataset generated by assigning categories to the lecture video transcripts gathered from e-learning portals. The performance of search is assessed based on the accuracy and time taken. Further the improved accuracy of the proposed indexing technique is compared with the accepted chain indexing technique.

• Proceedings of the KSPS conference
• /
• 2006.11a
• /
• pp.71-74
• /
• 2006

Many works have been done in the field of retrieving audio segments that contain human speeches without captions. To retrieve newly coined words and proper nouns, subwords were commonly used as indexing units in conjunction with query or document expansion. Among them, document expansion with subwords has serious drawback of large computation overhead. Therefore, in this paper, we propose Expected Matching Score based document expansion that effectively reduces computational overhead without much loss in retrieval precisions. Experiments have shown 13.9 times of speed up at the loss of 0.2% in the retrieval precision.

• 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%.

• International Journal of Contents
• /
• v.3 no.3
• /
• pp.6-14
• /
• 2007

In this paper, we design and implement a XML Repository System(XRS) that exploits the advantages of DBMSs and IRSs. Our scheme uses BRS to support full text indexing and content-based queries efficiently, and ORACLE to store XML documents, multimedia data, DTD and structure information. We design databases to manage XML documents including audio, video, images as well as text. We employ the non-composition model when storing XML documents into ORACLE. We represent structured information as ETID(Element Type Id), SORD(Sibling ORDer) and SSORD(Same Sibling ORDer). ETID is a unique value assigned to each element of DTD. SORD and SSORD represent an order information between sibling nodes and an order information among the sibling nodes with the same element respectively. In order to show superiority of our XRS, we perform various experiments in terms of the document loading time, document extracting time and contents retrieval time. It is shown through experiments that our XRS outperforms the existing XML document management systems. We also show that it supports various types of queries through performance experiments.