Filters








902 Hits in 7.3 sec

Re-Visiting The Music Segmentation Problem With Crowdsourcing

Cheng-I Wang, Gautham J. Mysore, Shlomo Dubnov
2017 Zenodo  
"Re-visiting the Music Segmentation Problem with Crowdsourcing", 18th International Society for Music Information Retrieval Conference, Suzhou, China, 2017.  ...  Inter-Annotator Analysis In [9] , the problem of subjectivity in music structural segmentation problem is studied by showing annotator effects with the two-way ANOVA factor analysis.  ... 
doi:10.5281/zenodo.1415944 fatcat:vfgpmkqhn5fcvecs4hocbkwqgi

Audio innovation and songs to spur change in global health: evidence from a national crowdsourcing open call for youth social innovation in Malaysia

Rayner Kay Jin Tan, Ralph Mpofu, Pradheep Kay, Darien Sebastian, Djordje Novakovic, Ying-Ru Jacqueline Lo, Joseph D Tucker
2022 BMJ Innovations  
This article explores the role of audio innovation to spur change in the context of a crowdsourcing open call for youth (18–30 years old) in Malaysia.MethodsA crowdsourcing open call for youth in Malaysia  ...  Building on the experience from this crowdsourcing open call, we also describe key considerations for open calls to incorporate audio innovations in low-resource settings.ConclusionAudio innovations like  ...  Acknowledgements We thank all participants, judges, steering committee members, and mentors in the Imagine The World  ... 
doi:10.1136/bmjinnov-2021-000905 fatcat:zwaojrmgfzfq3ehjql6amltxee

Local business ambience characterization through mobile audio sensing

He Wang, Dimitrios Lymberopoulos, Jie Liu
2014 Proceedings of the 23rd international conference on World wide web - WWW '14  
, it is feasible to train models that can simultaneously infer occupancy, human chatter, music, and noise levels in a business, with higher than 79% accuracy.  ...  We leverage the phone's microphone during this time to infer the occupancy and human chatter levels, the music type, as well as the music and noise levels in the business.  ...  In particular, we experiment with leveraging the whole audio recording of 15 seconds as a single segment, as well as with using 3-second segments.  ... 
doi:10.1145/2566486.2568027 dblp:conf/www/WangLL14 fatcat:2zm3lgqqnbbbdctcspde7ft3kq

Crowdsourcing for search evaluation

Vitor R. Carvalho, Matthew Lease, Emine Yilmaz
2011 SIGIR Forum  
With this study, we show that crowdsourcing is a perfectly viable alternative to evaluate music systems without the need for experts.  ...  Ground truths based on partially ordered lists were developed to cope with problems regarding relevance judgment, but they require such man-power to generate that the official MIREX evaluations had to  ...  Labs and in part by the University of Delaware Research Foundation.  ... 
doi:10.1145/1924475.1924481 fatcat:56ywunsa6vgdvmjmoulohmq5ye

A Novel Label Aggregation with Attenuated Scores for Ground-Truth Identification of Dataset Annotation with Crowdsourcing

Ratchainant THAMMASUDJARIT, Anon PLANGPRASOPCHOK, Charnyote PLUEMPITIWIRIYAWEJ
2017 IEICE transactions on information and systems  
labels, for a certain dataset, from crowdsourcing annotations -is a crucial task to make the dataset usable, e.g., for a supervised learning problem.  ...  To address the challenges, this paper introduces: 1) Attenuated score (A-score) -an indicator that locally measures annotator performance for segments of annotation sequences, and 2) label aggregation  ...  Jacob Whitehill to share the source code of GLAD implementation.  ... 
doi:10.1587/transinf.2016dap0024 fatcat:ay5pocxhrrbgbcb3i3zqfkwzsm

Competitive Remix Practice and Networks of Support in Electronic Dance Music Economies

Jonathan Karpetz
2004 Dancecult: Journal of Electronic Dance Music Culture  
In Electronic Dance Music (EDM), crowdsourced competitive remix platforms have reoriented certain practices into networks of competition, where winning distinction is often only part of a larger process  ...  of further enmeshing DJs, music producers and their supporters in the social media fueled ecosystems that these websites have created.  ...  crowdsourcing practices of providing a platform for forming a crowd to solve creative problems, while also pushing the undercurrent of competition that drives most crowdsourcing initiatives to the forefront  ... 
doi:10.12801/1947-5403.2014.06.02.02 fatcat:upvbkifgcza77kumeap7zqwnuu

Chimera

Chong Sun, Narasimhan Rampalli, Frank Yang, AnHai Doan
2014 Proceedings of the VLDB Endowment  
In particular, we argue that at large scales crowdsourcing is critical, but must be used in combination with learning, rules, and in-house analysts.  ...  Large-scale classification is an increasingly critical Big Data problem. So far, however, very little has been published on how this is done in practice.  ...  ., books, movies, musics, that share the same title (e.g., "The Hunger Games").  ... 
doi:10.14778/2733004.2733024 fatcat:s6ryzt5dsbanjhs7kqobloc4ua

ASR for Under-Resourced Languages From Probabilistic Transcription

Mark A. Hasegawa-Johnson, Preethi Jyothi, Daniel McCloy, Majid Mirbagheri, Giovanni M. di Liberto, Amit Das, Bradley Ekin, Chunxi Liu, Vimal Manohar, Hao Tang, Edmund C. Lalor, Nancy F. Chen (+4 others)
2017 IEEE/ACM Transactions on Audio Speech and Language Processing  
EEG distribution coding and text-derived phone language models were both shown to improve the quality of probabilistic transcripts derived from mismatched crowdsourcing.  ...  Second, mismatched crowdsourcing is a recent technique in which non-speakers of the language are asked to write what they hear, and their nonsense transcripts are decoded using noisy channel models of  ...  The podcasts contain utterances interspersed with segments of music and English.  ... 
doi:10.1109/taslp.2016.2621659 fatcat:6mpdktvutrfcjan4irxil34gyq

Mountain Peak Detection in Online Social Media [article]

Roman Fedorov
2015 arXiv   pre-print
The extraction algorithm then identifies the mountain peaks present in the photograph and their profiles.  ...  maps and a rendered view of the mountain silhouettes that should be seen from the observer's point of view.  ...  visited millions of places all around the world.  ... 
arXiv:1508.02959v1 fatcat:s7pku6p2bzeqlhfoizifhoewn4

Spatial Keyword Querying: Ranking Evaluation and Efficient Query Processing [article]

Ilkcan Keles
2018 PhD series, Technical Faculty of IT and Design, ˜Aalborg=ålborgœ University  
This work was partly supported by the National Natural Science Foundation of China and Fundamental Research Funds for the Central Universities.  ...  Acknowledgments Acknowledgements The authors would like to thank CrowdFlower. Jinpeng Chen's work was partly sponsored by a scholarship from the China Scholarship Council (CSC).  ...  Given a set of GPS records, Paper E addresses the problem of finding users' visits to PoIs. This problem statement covers two problems: Detecting the stops in the set, and stop assignment to PoIs.  ... 
doi:10.5278/vbn.phd.tech.00039 fatcat:x53exbaxcjd7bjq5g7uwexspqu

Bird detection in audio: a survey and a challenge [article]

Dan Stowell, Mike Wood, Yannis Stylianou, Hervé Glotin
2016 arXiv   pre-print
We review the state of the art in automatic bird sound detection, and identify a widespread need for tuning-free and species-agnostic approaches.  ...  We introduce new datasets and an IEEE research challenge to address this need, to make possible the development of fully automatic algorithms for bird sound detection.  ...  Big data problems also affect manual work with audio data, such as the manual browsing and data-mining of audio archives [10] .  ... 
arXiv:1608.03417v1 fatcat:ahdjswz7izcq3efgzh2nx7pbte

Bird detection in audio: A survey and a challenge

Dan Stowell, Mike Wood, Yannis Stylianou, Herve Glotin
2016 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)  
We review the state of the art in automatic bird sound detection, and identify a widespread need for tuning-free and species-agnostic approaches.  ...  We introduce new datasets and an IEEE research challenge to address this need, to make possible the development of fully automatic algorithms for bird sound detection.  ...  Big data problems also affect manual work with audio data, such as the manual browsing and data-mining of audio archives [10] .  ... 
doi:10.1109/mlsp.2016.7738875 dblp:conf/mlsp/StowellWSG16 fatcat:rhvxdlxmc5c2jdzfh42ivsz6wm

Idiom—based features in sentiment analysis: Cutting the Gordian knot

Irena Spasic, Lowri Williams, Andreas Buerki
2017 IEEE Transactions on Affective Computing  
list of idioms without the knowledge acquisition overhead previously associated with this task, thereby fully automating the original approach.  ...  Although the latter improvement is not as high as the one achieved with the manually engineered features, it has got the advantage of being more general in a sense that it can readily utilize an arbitrary  ...  ACKNOWLEDGMENTS LW gratefully acknowledges the support of the Engineering and Physical Sciences Research Council (ref: 1511905).  ... 
doi:10.1109/taffc.2017.2777842 fatcat:pao6lmvm7jfgxis7qy26dkol3m

Semantic Crowdsourcing of Soundscapes Heritage: A Mojo Model for Data-Driven Storytelling

Marina Eirini Stamatiadou, Iordanis Thoidis, Nikolaos Vryzas, Lazaros Vrysis, Charalampos Dimoulas
2021 Sustainability  
The current paper focuses on the development of an enhanced Mobile Journalism (MoJo) model for soundscape heritage crowdsourcing, data-driven storytelling, and management in the era of big data and the  ...  In this view, context- and location-aware mobile services can be combined with state-of-the-art machine and deep learning approaches to offer multilevel semantic analysis monitoring of sound-related heritage  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/su13052714 doaj:ff6654e687b84c8d97b3190f64a9fe40 fatcat:7cpbmkhuwferlk2t45actns4km

Crowdsourcing A Real-World On-Line Query By Humming System

Arefin Huq, Mark Cartwright, Bryan Pardo
2010 Proceedings of the SMC Conferences  
ACKNOWLEDGEMENTS We would like to thank the National Science Foundation for funding to do this research. This work was supported by NSF Grant number IIS-0812314.  ...  Finding the desired recording with this indexing scheme can be a problem for those who do not know the metadata for the desired piece.  ...  Our system allows re-tuning of the weight of such parameters after deployment, as the composition of the database and the user queries shift over time [18] .  ... 
doi:10.5281/zenodo.849745 fatcat:p5cfhsdbcnhm5nipnufmh6sm5u
« Previous Showing results 1 — 15 out of 902 results