Filters








270 Hits in 10.1 sec

Unsupervised Spoken Term Discovery on Untranscribed Speech [article]

Man-Ling Sung
2020 arXiv   pre-print
By using information retrieval technology such as word embedding and TFIDF, it is shown that the discovered keywords can be further used for topic comparison.  ...  Unsupervised pattern discovery searches for repetitive patterns in the "phoneme" sequences. The discovered patterns can be grouped to determine the keywords of the audio.  ...  Unsupervised word discovery Spoken term detection indexes speech based on the content efficiently.  ... 
arXiv:2011.14060v1 fatcat:vqxrmzjq35codkddbza6fdd4a4

BASIL: Effective Near-Duplicate Image Detection Using Gene Sequence Alignment [chapter]

Hung-sik Kim, Hau-Wen Chang, Jeongkyu Lee, Dongwon Lee
2010 Lecture Notes in Computer Science  
We propose two unsupervised feature selection methods based on the notions of Non-Localness and Geometric-Localness to prune noisy data in the content.  ...  We also propose a heuristics-based method to extract n-gram keyphrases from noisy textual content by taking the importance of sub-term keywords into consideration. iii  ...  For example, R GI j,k is the rating of group j on image k. • Index variable. h, i, j, k are used to index a matrix or vector. • Rank K. K is the dimensionality of the latent factor. • Size.  ... 
doi:10.1007/978-3-642-12275-0_22 fatcat:ou4wo4a6efdabkipzbkaxd5cyi

Speech Retrieval [chapter]

Ciprian Chelba, Timothy J. Hazen, Bhuvana Ramabhadran, Murat Saraçlar
2011 Spoken Language Understanding  
This chapter provides an overview of the common tasks and data sets, evaluation metrics, and algorithms most commonly used in this growing area of research.  ...  Classical audio mining has focused on keyword spotting techniques that can look for topics or specific phrases in the audio (Hansen et al. 2005) .  ...  Using sub-words for indexing requires efficient methods for indexing and retrieving sequences.  ... 
doi:10.1002/9781119992691.ch15 fatcat:o36ulm7kh5dxvhm6alb4yz3qvy

The Flipped Classroom: Teaching the Basic Science Process Skills to High-Performing 2nd Grade Students of Miriam College Lower School

Mark Kenneth Camiling
2017 IAFOR Journal of Education  
Keywords Immediately after the abstract, provide a maximum of 6 keywords.  ...  The experimental group was asked to watch at home researcher-made videos that teach the basic science process skills.  ...  Footnotes Footnotes should be used sparingly. Number them consecutively throughout the article, using superscript Arabic numbers.  ... 
doi:10.22492/ije.5.si.10 fatcat:jfbf2vngdfas5ivj6ttqtlhe7u

A Model for the Application of Automatic Speech Recognition for Generating Lesson Summaries

Phillip Blunt, Bertram Haskins
2021 Advances in Science, Technology and Engineering Systems  
spotting or continuous speech recognition.  ...  on noise-free speech, contrasted with a 96,93% accuracy in keyword identification and association on noise-polluted speech using a noise-cancellation technique.  ...  Automatic speech recognition (ASR) has been applied in assistive technologies for tasks such as closed captioning, voice search, command detection as well as keyword identification.  ... 
doi:10.25046/aj060260 fatcat:sj47vcoeljhzblc7gnnsksvt5i

Navigating within news collections using tag-flakes

Luigi Di Caro, K. Selçuk Candan, Maria Luisa Sapino
2011 Journal of Visual Languages and Computing  
The use of tag clouds is common for presenting frequently occurring tags or keywords in a collection to the users.  ...  However, instead of using this latent semantic space to simply cluster and index the documents (as commonly done in many existing schemes), TMine analyzes the relationships between tags in this semantic  ...  In this way, they obtain an index on keywords that splits the input according to its content.  ... 
doi:10.1016/j.jvlc.2010.11.001 fatcat:y5radxsvdvddncd47mmcqcat3q

Automatic Summarization

Martha Larson
2012 Foundations and Trends in Information Retrieval  
This growth has motivated extensive research on techniques and technologies that facilitate reliable indexing and retrieval.  ...  Speech media, that is, digital audio and video containing spoken content, has blossomed in recent years. Large collections are accruing on the Internet as well as in private and enterprise settings.  ...  The indexing features are extracted from the speech signal using a keyword spotting system.  ... 
doi:10.1561/1500000020 fatcat:o424mjxnp5abbexhjsobtom2ry

Proceedings of eNTERFACE 2015 Workshop on Intelligent Interfaces [article]

Matei Mancas, Christian Frisson, Joëlle Tilmanne, Nicolas d'Alessandro, Petr Barborka, Furkan Bayansar, Francisco Bernard, Rebecca Fiebrink, Alexis Heloir, Edgar Hemery, Sohaib Laraba, Alexis Moinet (+58 others)
2018 arXiv   pre-print
The team would also like to thank Jérôme Hennebert, lecturer at the The authors would like to thank the local organizers of eNTEFACE'15 for their kindness, their local assistance regarding logistics, their  ...  The team would like to thank Metapraxis for supporting this project and lending us one of the tablets for the experiments.  ...  The extracted features are then used as the basis for indexing the videos, which necessitated specific approaches as indexing based on such features can generally not rely on indexing schemes evolved for  ... 
arXiv:1801.06349v1 fatcat:qauytivdq5axxis2xlknp3r2ne

Topic transition detection using hierarchical hidden Markov and semi-Markov models

Dinh Q. Phung, T. V. Duong, S. Venkatesh, Hung H. Bui
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
In this paper we introduce a probabilistic framework to exploit hierarchy, structure sharing and duration information for topic transition detection in videos.  ...  Furthermore, the use of the Coxian distribution in the S-HSMM makes it tractable to deal with long sequences in video.  ...  [9] propose an automatic indexing scheme for news video where shots are indexed based on the image content and keywords into five categories: speech/report, anchor, walking, gathering, and computer  ... 
doi:10.1145/1101149.1101153 dblp:conf/mm/PhungDVB05 fatcat:5ijcwesr4fhi7guwp5aytsd67y

Audiovisual Information Fusion in Human–Computer Interfaces and Intelligent Environments: A Survey

Shankar T. Shivappa, Mohan Manubhai Trivedi, Bhaskar D. Rao
2010 Proceedings of the IEEE  
Human brain processes the audio and video modalities extracting complementary and robust information from them.  ...  The fusion strategy used tends to depend mainly on the model, probabilistic or otherwise, used in the particular task to process sensory information to obtain higher level semantic information.  ...  We sincerely thank the reviewers for their valuable advise which has helped us enhance the content as well as the presentation of the paper.  ... 
doi:10.1109/jproc.2010.2057231 fatcat:lfzgfmn2hjdq7h6o5txva3oapq

FINUT abstracts

2020 Annals of Nutrition and Metabolism  
Keywords: Assistance in emergencies/ food assistance/ risk management.  ...  Keywords: Emergency feeding/ food assistance/ food services/ risk management.  ...  , proposal to evaluate the use of donated food as part of a food assistance programs.  ... 
doi:10.1159/000511826 pmid:33040070 fatcat:7f7rwo7iubgefac5grtatkja74

The AI Index 2021 Annual Report [article]

Daniel Zhang, Saurabh Mishra, Erik Brynjolfsson, John Etchemendy, Deep Ganguli, Barbara Grosz, Terah Lyons, James Manyika, Juan Carlos Niebles, Michael Sellitto, Yoav Shoham, Jack Clark (+1 others)
2021 arXiv   pre-print
Welcome to the fourth edition of the AI Index Report.  ...  The AI Index Report tracks, collates, distills, and visualizes data related to artificial intelligence.  ...  The terms searched for were based on the issues exposed and identified in papers below, and also on the topics called for discussion in the First AAAI/ACM Conference on AI, Ethics, and Society.  ... 
arXiv:2103.06312v1 fatcat:52qwvzv7jndxzaagyiro6koyza

Modified group delay feature based total variability space modelling for speaker recognition

Srikanth R. Madikeri, Asha Talambedu, Hema A. Murthy
2014 International Journal of Speech Technology  
Project Title :Text Transcription of Technical Video Lectures and Creation of Searchable Video Index, Metadata and Online Quizzes Coordinators : Mangala Sunder and Hema A Murthy Total : 3.45 crores  ...  Murthy, "Acoustic Segmentation Using Group Delay Functions and Its Relevance To Spoken Keyword Spotting", Text Speech and Dialogue, pp.496-504, Sept 2012. 37.  ... 
doi:10.1007/s10772-014-9243-7 fatcat:kkkyx63jf5eu7jav6x4xzogdeu

STUD 2019 Blank Page

2019 2019 First International Conference on Smart Technology & Urban Development (STUD)  
internet for the purpose of academic, social media, communication with foreigners, and research� Keywords-information technology for education communication; readiness of information technology; ASEAN  ...  Author Index ��������������������������������������������������������������������������������������������������������������������� 88 1 The readiness of information technology of Rajamangala University  ...  The attribute is used as supervision for unsupervised learning such as [19] leverage the model trained from labeled source data and transfer the knowledge to unlabeled data by using a joint attribute  ... 
doi:10.1109/stud49732.2019.9018735 fatcat:w2isrk4dsfg3fneffmbkwv5c7m

Developing a Collaborative MOOC Learning Environment utilizing Video Sharing with Discussion Summarization as Added-Value

Mohannad Al-Mousa, Jinan Fiaidhi
2014 International Journal of Multimedia and Ubiquitous Engineering  
Finally, we evaluate our result using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) system, which compares our automated summary to human extracted summaries.  ...  Current LMS -in particular MOOC providers -offer many advanced content delivery techniques: interactive video, active retrieval practices, and quizzes to enhance the pedagogical process.  ...  The lecturer states that the reduction of sun spots could in fact reduce or even pause the effects of global warming.  ... 
doi:10.14257/ijmue.2014.9.11.38 fatcat:dlkydmpm2bardefwu65gczghxe
« Previous Showing results 1 — 15 out of 270 results