2,138 Hits in 6.5 sec

Proceedings of the 17th Dutch-Belgian Information Retrieval Workshop [article]

Alex Brandsen, Anne Dirkson, Wessel Kraaij, Wout Lamers, Suzan Verberne, Hugo de Vos, Gineke Wiggers
2018 arXiv   pre-print
This volume contains the papers presented at DIR 2018: 17th Dutch-Belgian Information Retrieval Workshop (DIR) held on November 23, 2018 in Leiden.  ...  The committee accepted 4 short papers presenting novel work, 3 demo proposals, and 8 compressed contributions (summaries of papers recently published in international journals and conferences).  ...  ACKNOWLEDGMENTS The authors wish to thank the employees of Legal Intelligence for their cooperation in this research. ACKNOWLEDGEMENTS Supported by "Google Digital News Initiative" 5  ... 
arXiv:1812.04265v1 fatcat:ezpjxeybmnfhlooy6sk4yo62lm


Shahriar Nirjon, Robert Dickerson, John Stankovic, Guobin Shen, Xiaofan Jiang
2013 Proceedings of the 14th Workshop on Mobile Computing Systems and Applications - HotMobile '13  
We perform an empirical study to quantify the sparseness in speech recorded on a smartphone and use it to obtain a highly accurate and sparse approximation of a widely used feature of speech called the  ...  We name the new feature the sparse MFCC or sMFCC, in short. We experimentally determine the trade-offs between the approximation error and the expected speedup of sMFCC.  ...  This method has several limitations such as the requirement for an uninterrupted Internet connectivity and high bandwidth, and the associated expense of sending a large chunk of audio data over the cellular  ... 
doi:10.1145/2444776.2444787 dblp:conf/wmcsa/NirjonDSSJ13 fatcat:2hnk4ccmgfbtlaqil6wxrvyqhe

Music Genres Classification using Text Categorization Method

Kai Chen, Sheng Gao, Yongwei Zhu, Qibin Sun
2006 2006 IEEE Workshop on Multimedia Signal Processing  
In this paper, we propose a new framework using text category methods to classify music genres. This framework is different from current methods for Music genre classification.  ...  From the experimental results, we could achieve an average recall over 70% for ten musical genres.  ...  HMM is a powerful framework for learning and recognizing the temporal patterns and has been applied in the music summary based on temporal information [7] , thus we adopt HMM to explore music symbols  ... 
doi:10.1109/mmsp.2006.285301 dblp:conf/mmsp/ChenGZS06 fatcat:ao6rutv3zbh3fpb246yl3fx25i

Periodic signal extraction with frequency-selective amplitude modulation and global time-warping for music signal decomposition

Mahdi Triki, Dirk T.M. Slock, Ahmed Triki
2008 2008 IEEE 10th Workshop on Multimedia Signal Processing  
A key building block in music transcription and indexing operations is the decomposition of music signals into notes.  ...  Time-warping allows for some limited global frequency modulation.  ...  More accurate techniques can be proposed for the instantaneous frequency estimation (High Resolution (HR) methods [12] ) or tracking (such as frequency-locked loop signal tracking [16] ).  ... 
doi:10.1109/mmsp.2008.4665215 dblp:conf/mmsp/TrikiST08 fatcat:dfto2mnzxvaupokjfo2pczn2ae

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 11th Summer Workshop on Multimodal Interfaces eNTERFACE 2015 was hosted by the Numediart Institute of Creative Technologies of the University of Mons from August 10th to September 2015.  ...  nice schedule of social events.The authors would also thanks to Radhwan and Ambroise for their sympathy and for sharing good and bad moments with us during the workshop.  ...  The team would like to thank Metapraxis for supporting this project and lending us one of the tablets for the experiments.  ... 
arXiv:1801.06349v1 fatcat:qauytivdq5axxis2xlknp3r2ne

Multi-modality web video categorization

Linjun Yang, Jiemin Liu, Xiaokang Yang, Xian-Sheng Hua
2007 Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07  
We conduct a set of comprehensive experiments for evaluating the effectiveness of the proposed feature representations over different classifiers such as Support Vector Machine (SVM), Gaussian Mixture  ...  Our experiments on a large-scale dataset with 11k web videos (nearly 450 hours in total) demonstrate that (1) the proposed multimodal feature representation is effective for web video categorization, and  ...  This will result in the sparseness of the vector model.  ... 
doi:10.1145/1290082.1290119 dblp:conf/mir/YangLYH07 fatcat:lpiiw2e3kvbuleejndhhcns3zu

Audio-Visual Classification of Sports Types

Rikke Gade, Mohamed Abou-Zleikha, Mads Graesboll Christensen, Thomas B. Moeslund
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
In this work we propose a method for classification of sports types from combined audio and visual features extracted from thermal video.  ...  From these, four motion features are extracted and combined directly with audio features for classification.  ...  The applications of these methods are, e.g., replays during games and short summaries for news channels. One example of this is analysis of TV productions from soccer matches.  ... 
doi:10.1109/iccvw.2015.104 dblp:conf/iccvw/GadeACM15 fatcat:t24lxktw4fd7xhajhfz7owlg64

CQT-based Convolutional Neural Networks for Audio Scene Classification

Thomas Lidy, Alexander Schindler
2016 Workshop on Detection and Classification of Acoustic Scenes and Events  
A popular choice for input to a Convolutional Neural Network in audio classification problems are Mel-transformed spectrograms.  ...  In this paper, we propose a parallel Convolutional Neural Network architecture for the task of classifying acoustic scenes and urban sound scapes.  ...  ACKNOWLEDGMENTS We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X GPU used for this research.  ... 
dblp:conf/dcase/LidyS16 fatcat:aoefz2vtrjbtlb25msbrvlgtny

Contour representations of sound

Yoonseob Lim, Barbara Shinn-Cunningham, Timothy Gardner
2011 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)  
By analysing the signal in many time-scales, an over-complete set of shapes is generated for a given sound.  ...  We consider how the continuity of form in natural sounds may be used to discover sparse time-frequency representations.  ...  We note in closing that neural auditory processing could conceivably involve a similar contour representation for sound.  ... 
doi:10.1109/aspaa.2011.6082322 dblp:conf/waspaa/LimSG11 fatcat:6nshvbvyrbdhhiz6aq5z4qv67u

An N-gram model for unstructured audio signals toward information retrieval

Samuel Kim, Shiva Sundaram, Panayiotis Georgiou, Shrikanth Narayanan
2010 2010 IEEE International Workshop on Multimedia Signal Processing  
An N -gram modeling approach for unstructured audio signals is introduced with applications to audio information retrieval.  ...  The proposed N -gram approach aims to capture local dynamic information in acoustic words within the acoustic topic model framework which assumes an audio signal consists of latent acoustic topics and  ...  For music information retrieval applications, they proposed a new iterative segmentation method based on Viterbi decoding and Baum-Welch estimation.  ... 
doi:10.1109/mmsp.2010.5662068 dblp:conf/mmsp/KimSGN10 fatcat:ygvqqp5jebcujfdapam2maho5q

Two systems for automatic music genre recognition

Bob L. Sturm
2012 Proceedings of the second international ACM workshop on Music information retrieval with user-centered and multimodal strategies - MIRUM '12  
We re-implement and test two state-of-the-art systems for automatic music genre classification; but unlike past works in this area, we look closer than ever before at their behavior.  ...  Our results suggest that neither high-performing system has a capacity to recognize music genre.  ...  Its use for music genre recognition was first proposed in [4] .  ... 
doi:10.1145/2390848.2390866 dblp:conf/mm/Sturm12a fatcat:qaegjsrikjb7njwdoez5gpr7ta

Discriminativetensor dictionaries and sparsity for speaker identification

S. Zubair, W. Wang, J. A. Chambers
2014 2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)  
Our results show the supremacy of our proposed method over other approaches.  ...  This algorithm, named as GT-D, is then used for the speaker identification.  ...  Benetos et al. in [5] introduced non-negative PARAFAC decomposition with multiplicative updates and designed a classifier from learned PARAFAC factors for the classification of musical genres.  ... 
doi:10.1109/hscma.2014.6843247 dblp:conf/hscma/ZubairWC14 fatcat:jx2w6llgsfhs7loefb3rxhpzfu

Profiling podcast-based content distribution

Anirban Banerjee, Michalis Faloutsos, Laxmi N. Bhuyan
2008 IEEE INFOCOM 2008 - IEEE Conference on Computer Communications Workshops  
to a heavy tail Pareto distribution for web files).  ...  We start by conducting extensive active measurements to characterize 875 popular podcast streams for over a month.  ...  INTRODUCTION Podcasts are a push-based mechanism for distributing multimedia files such as audio programs or music videos over the Internet.  ... 
doi:10.1109/infocom.2008.4544578 fatcat:45oyfsfkwjhkliogtzmlfg5g3e

Towards unsupervised pattern discovery in speech

A. Park, J.R. Glass
2005 IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.  
for unsupervised word discovery.  ...  Some preliminary qualitative results for both experiments are shown and the implications for future work and applications are discussed.  ...  Likewise, we can envision generating direct audio summaries by simply playing back instances of the salient words found by clustering.  ... 
doi:10.1109/asru.2005.1566529 fatcat:cvv23d5mfffjdaiom7ann2zfhi

Automatic measurement and analysis of the child verbal communication using classroom acoustics within a child care center

Maryam Najafian, Dwight Irvin, Ying Luo, Beth Rous, John Hl Hansen
2016 Workshop on Child Computer Interaction  
Detecting speaker turns is necessary before more in depth subsequent analysis of audio such as word count, speech recognition, and keyword spotting which can contribute to the design of future learning  ...  spaces specifically designed for typically developing children, or those at-risk with communication limitations.  ...  value has a significant impact on performance of SAD on speech-sparse and non-speech regions.  ... 
doi:10.21437/wocci.2016-10 dblp:conf/wocci/NajafianILRH16 fatcat:oyixnnlurfexbebvhvqomue5y4
« Previous Showing results 1 — 15 out of 2,138 results