1,267 Hits in 3.8 sec

Multi-Lingual Broadcast News Retrieval

Alexander G. Hauptmann, Ming-yu Chen, Michael G. Christel, D. Das, Wei-Hao Lin, Rong Yan, Jie Yang, Gerhard Backfried, Xiao Wu
2006 TREC Video Retrieval Evaluation  
We build text classifier on this multi-lingual feature using SVM with a linear kernel. We evaluated the proposed multilingual text features on the development set of TRECVID'06.  ...  To process a new query, we first classify it into a specific query type and then use the corresponding retrieval model to find its relevant shots.  ... 
dblp:conf/trecvid/HauptmannCCDLY006 fatcat:wjl7ftqu4fem5cmfaet7vmq2sm

Multi-Lingual Broadcast News Retrieval

Alexander Hauptmann, Ming-Yu Chen, Michael G Christel, D. Das, W.-H. Lin, R. Yan, J. Yang, G. Backfried, X. Wu
We build text classifier on this multi-lingual feature using SVM with a linear kernel. We evaluated the proposed multilingual text features on the development set of TRECVID'06.  ...  To process a new query, we first classify it into a specific query type and then use the corresponding retrieval model to find its relevant shots.  ... 
doi:10.1184/r1/6607553 fatcat:ph46cpfkbrgntmi7nwvbfaqxiy

Mandarin–English Information (MEI): investigating translingual speech retrieval

Helen M. Meng, Berlin Chen, Sanjeev Khudanpur, Gina-Anne Levow, Wai-Kit Lo, Douglas Oard, Patrick Schone, Karen Tang, Hsin-min Wang, Jianqiang Wang
2004 Computer Speech and Language  
Our system accepts an entire English news story (text) as query, and retrieves relevant Chinese broadcast news stories (audio) from the document collection.  ...  The multi-scale approach can be divided into three subtasks -multi-scale query formulation, multi-scale audio indexing (by speech recognition) and multi-scale retrieval.  ...  The TDT multi-lingual collection includes English and Mandarin news text as well as (audio) broadcast news.  ... 
doi:10.1016/j.csl.2003.09.003 fatcat:ixr4gkjaqrhs7b7gkrabq7p3ca

Automatic event generation from multi-lingual news stories

Kin Hui, Wai Lam, Helen M. Meng
2001 Proceedings of the first ACM/IEEE-CS joint conference on Digital libraries - JCDL '01  
We propose a novel approach for automatic generation of topically-related events from multi-lingual news sources. Named entity terms are extracted automatically from the news content.  ...  Thus, the capability of identifying whether multi-lingual news are discussing the same event is one of the challenges of the event discovery task.  ...  GROSS TRANSLATION In order to determine whether multi-lingual news stories are topically-related, we conduct translation on the story representation of Chinese stories to English so that we can perform  ... 
doi:10.1145/379437.379442 dblp:conf/jcdl/HuiLM01 fatcat:vtecqu2x75ft7k5cp26qyd574a

Phonetic name matching for cross-lingual Spoken Sentence Retrieval

Heng Ji, Ralph Grishman, Wen Wang
2008 2008 IEEE Spoken Language Technology Workshop  
Cross-lingual Spoken Sentence Retrieval (CLSSR) remains a challenge, especially for queries including OOV words such as person names.  ...  conversation shows and 22 broadcast news shows) from GALE Y2 MT dev set.  ...  We used part of the GALE 1 Y2 audio MT development corpus as our candidate documents (19 broadcast conversation shows and 26 broadcast news shows, in total 668 sentences). 53 queries were constructed by  ... 
doi:10.1109/slt.2008.4777895 dblp:conf/slt/JiGW08 fatcat:uzvykvc645bthcf2v5cn634pui

Towards multilingual interoperability in automatic speech recognition

Martine Adda-Decker
2001 Speech Communication  
news transcripts can be broadcast transcriptions. used for indexing or document retrieval tasks (NIST SDR program).  ...  ) and German broadcast news transcription. during 1996.  ... 
doi:10.1016/s0167-6393(00)00092-3 fatcat:t6xoinpch5fkfp2457zpjwmuey

The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring

Ulrich Germann, Renārs Liepins, Guntis Barzdins, Didzis Gosko, Sebastião Miranda, David Nogueira
2018 Proceedings of ACL 2018, System Demonstrations  
factual claims in these news items.  ...  The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes  ...  Conclusion The SUMMA Platform successfully integrates a multitude of state-of-the-art NLP components to provide an integrated platform for multi-lingual media monitoring and analysis.  ... 
doi:10.18653/v1/p18-4017 dblp:conf/acl/GermannLBGMN18 fatcat:xjrbxpi77jbdfiod7yumkxjzb4

Cross-lingual audio-to-text alignment for multimedia content management

Dau-Cheng Lyu, Ren-Yuan Lyu, Yuang-Chin Chiang, Chun-Nan Hsu
2008 Decision Support Systems  
In our case, we have a huge digital archive of audio broadcast news in Taiwanese, but we do not have transcriptions for it.  ...  Meanwhile, we have a collection of related text-based news stories, but they are written in Chinese characters.  ...  The purpose is to evaluate the feasibility of our cross-lingual alignment approach for managing multi-media cross-lingual contents.  ... 
doi:10.1016/j.dss.2007.07.003 fatcat:t5seflrjifcolnrouwvb6d2sge

Novelty detection for cross-lingual news stories with visual duplicates and speech transcripts

Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo
2007 Proceedings of the 15th international conference on Multimedia - MULTIMEDIA '07  
To effectively search, retrieve, browse and track cross-lingual news stories, a news story similarity measure plays a critical role in assessing the novelty and redundancy among them.  ...  In this paper, we explore the novelty and redundancy detection with visual duplicates and speech transcripts for cross-lingual news stories.  ...  CONCLUSION Novelty and redundancy detection for cross-lingual broadcast news stories is a substantial task for news story search, retrieval, and tracking.  ... 
doi:10.1145/1291233.1291274 dblp:conf/mm/WuHN07 fatcat:sxeesbepprc5zgwxdzujm4mlx4

Cross-Language Spoken Document Retrieval on the TREC SDR Collection [chapter]

N. Bertoldi, M. Federico
2003 Lecture Notes in Computer Science  
They include automatic transcripts of American English broadcast news, short topics written in English, and relevance assessments.  ...  This paper presents preliminary experiments on crosslanguage spoken document retrieval (SDR) carried out on a benchmark assembled at ITC-irst.  ...  Cross-language (CL) information retrieval (IR) provides an important way to access multi-lingual documents.  ... 
doi:10.1007/978-3-540-45237-9_41 fatcat:5auavwilavaz7naoclcxyjty54

Design of a Cross-Media Indexing System [chapter]

Murat Yakıcı, Fabio Crestani
2006 Lecture Notes in Computer Science  
There is a lack of an integrated technology that will increase effective usage of the vast and heterogeneous multi-lingual and multimedia digital content.  ...  This paper gives an overview of the project, CMIC's enrichment approach and its support for retrieval.  ...  and multi-lingual digital content across different sources (such as TV, radio, Web).  ... 
doi:10.1007/11863878_47 fatcat:xlacoblq45dvhatis46tdusoj4

Introduction to the special issue on semantic analysis for interactive multimedia services

Yiannis Kompatsiaris, Yannis Avrithis, Noel E. O'Connor
2008 Signal processing. Image communication  
Technologies for retrieving semantic information from multimedia content potentially enable new applications and services for both commercial and personal end users.  ...  The system is also potentially extensible to other content analysis modalities (e.g. audio) and supports multi-lingual functionality.  ...  Luo, Fan and Sato present a novel scheme for effective analysis, retrieval and exploration of large-scale news video collections by performing multi-modal video content analysis and synchronization.  ... 
doi:10.1016/j.image.2008.05.001 fatcat:wdhtwoopyjfvvpmp675e3wz4vu

Processing broadcast audio for information access

Jean-Luc Gauvain, Lori Lamel, Gilles Adda, Martine Adda-Decker, Claude Barras, Langzhou Chen, Yannick de Kercadio
2001 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics - ACL '01  
At LIMSI, broadcast news transcription systems have been developed for English, French, German, Mandarin and Portuguese, and systems for other languages are under development.  ...  One rapidly expanding application area is the processing of broadcast audio for information access.  ...  Automatic processing carried out on contemporaneous data sources in different languages can serve for multi-lingual indexation and retrieval.  ... 
doi:10.3115/1073012.1073014 dblp:conf/acl/GauvainLAABCK01 fatcat:qeuwmf4rjnerdieogaqszdld34

Evaluation campaigns and TRECVid

Alan F. Smeaton, Paul Over, Wessel Kraaij
2006 Proceedings of the 8th ACM international workshop on Multimedia information retrieval - MIR '06  
TV news.  ...  The TREC Video Retrieval Evaluation (TRECVid) is an international benchmarking activity to encourage research in video information retrieval by providing a large test collection, uniform scoring procedures  ...  CLEF tests aspects of mono-and cross-lingual IR through a variety of 8 different tracks including mono-, bi-and multi-lingual document retrieval on news, mono-and cross-lingual retrieval on structured  ... 
doi:10.1145/1178677.1178722 dblp:conf/mir/SmeatonOK06 fatcat:oecxegqkqzb3zmkge4y62vbpga

Intelligent Multimedia Communication [chapter]

Mark Maybury, Oliviero Stock, Wolfgang Wahlster
1998 Lecture Notes in Computer Science  
We conclude describing several new research issues that systems of systems raise.  ...  Or consider that in broadcast news spoken language transcription, the best word error rates are currently around 10% for broadcast news anchor speech.  ...  This work will enable new application areas for relatively unexplored tasks including: • Multimodal/lingual information access • Multimodal/lingual presentation generation (summarization) • Multimodal/  ... 
doi:10.1007/3-540-49653-x_1 fatcat:jbd4454lnzc23nrhoma4v3u2ge
« Previous Showing results 1 — 15 out of 1,267 results