Chua, Victoria Y. H.;Liu, Hexin;Perera, Leibny Paola Garcia;Woon, Fei Ting;...
To enhance the reliability and robustness of language identification (LID) and languag...
more
30/05/2023
To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and in-the-wild English-Mandarin code-switching, child-directed speech in non-standard accents with diverse language-mixing patterns recorded in a variety of home environments. This report describes the corpus, as well as LID and LD results for our baseline and several systems submitted to the MERLIon CCS challenge using the corpus.
Comment: Accepted by Interspeech 2023, 5 pages, 2 figures, 3 tables
Comment: Accepted by Interspeech 2023, 5 pages, 2 figures, 3 tables
Subject terms:
Electrical Engineering and Systems Science - Audio and Speech ProcessingContent provider:
arXiv
View this record from Arxiv
Perera, Leibny Paola Garcia;Chua, Y. H. Victoria;Liu, Hexin;Woon, Fei Ting;...
This paper introduces the inaugural Multilingual Everyday Recordings- Language Identif...
more
30/05/2023
This paper introduces the inaugural Multilingual Everyday Recordings- Language Identification on Code-Switched Child-Directed Speech (MERLIon CCS) Challenge, focused on developing robust language identification and language diarization systems that are reliable for non-standard, accented, spontaneous code-switched, child-directed speech collected via Zoom. Aligning closely with Interspeech 2023 theme, the main objectives of this inaugural challenge are to present a unique first-of-its-kind Zoom videocall dataset featuring English-Mandarin spontaneous code-switched child-directed speech, benchmark the current and novel language identification and language diarization systems in a code-switching scenario including extremely short utterances, and test the robustness of such systems under accented speech. The MERLIon CCS challenge features two task: language identification (Task 1) and language diarization (Task 2). Two tracks, open and closed, are available for each task, differing by the volume of data systems can be trained on. This paper describes the dataset, dataset annotation protocol, challenge tasks, open and closed tracks, evaluation metrics, and evaluation protocol.
Comment: Evaluation plan for Interspeech 2023 special session "MERLIon "
Comment: Evaluation plan for Interspeech 2023 special session "
Subject terms:
Electrical Engineering and Systems Science - Audio and Speech ProcessingContent provider:
arXiv
Anit Mukherjee;Anit Mukherjee
The Merlion and the Ashoka: Singapore-India Strategic Ties examines the historical evo...
more
2015
The Merlion and the Ashoka: Singapore-India Strategic Ties examines the historical evolution and future prospects of the strategic and defence ties between these two nations. India, which considers Singapore to be one of its closest partners in Southeast Asia, has offered Singapore unprecedented access to training facilities, including basing equipment on Indian soil. In turn, Singapore has a close defence dialogue at various levels with India and active military cooperation at the tactical and operational levels. How did the two countries attain such an unprecedented level of defence cooperation and what were the challenges they had to overcome? Combining perspectives from policy-makers, academics and military officers, this book examines different aspects surrounding this question. While exploring the future trajectory of Singapore-India relations, it makes recommendations on how to enhance this strategic partnership.
Subject terms:
International cooperationContent provider:
eBook Collection (EBSCOhost)
eBook
Bhatnagar, Aadyot;Kassianik, Paul;Liu, Chenghao;Lan, Tian;Yang, Wenzhuo;Cas...
We introduce Merlion, an open-source machine learning library for time series. It feat...
more
19/09/2021
We introduce Merlion , an open-source machine learning library for time series. It features a unified interface for many commonly used models and datasets for anomaly detection and forecasting on both univariate and multivariate time series, along with standard pre/post-processing layers. It has several modules to improve ease-of-use, including visualization, anomaly score calibration to improve interpetability, AutoML for hyperparameter tuning and model selection, and model ensembling. Merlion also provides a unique evaluation framework that simulates the live deployment and re-training of a model in production. This library aims to provide engineers and researchers a one-stop solution to rapidly develop models for their specific time series needs and benchmark them across multiple time series datasets. In this technical report, we highlight Merlion's architecture and major functionalities, and we report benchmark numbers across different baseline models and ensembles.
Comment: 22 pages, 1 figure, 14 tables
Comment: 22 pages, 1 figure, 14 tables
Subject terms:
Computer Science - Machine Learning - Computer Science - Mathematical Software - Statistics - Machine LearningContent provider:
arXiv
This Image of Themselves": (Re)Discovering the Merlion's Liminality.
Academic Journal
|
Asiatic: IIUM Journal of English Language & Literature. Dec2013, Vol. 7 Issue 2, p245-263. 19p.
Please log in to see more details
Chung, Ian
Academic Journal
|
Asiatic: IIUM Journal of English Language & Literature. Dec2013, Vol. 7 Issue 2, p245-263. 19p.
Please log in to see more details
PDF
Bhatnagar, Aadyot;Kassianik, Paul;Chenghao Liu;Tian Lan;Wenzhuo Yang;Cassiu...
Academic Journal
|
Journal of Machine Learning Research. 2023, Vol. 24, p1-6. 6p.
Please log in to see more details
We introduce Merlion, an open-source machine learning library for time series. It feat...
more
Journal of Machine Learning Research. 2023, Vol. 24, p1-6. 6p.
We introduce Merlion , an open-source machine learning library for time series. It features a unified interface for many commonly used models and datasets for forecasting and anomaly detection on both univariate and multivariate time series, along with standard pre/postprocessing layers. It has several modules to improve ease-of-use, including a no-code visual dashboard, anomaly score calibration to improve interpetability, AutoML for hyperparameter tuning and model selection, and model ensembling. Merlion also provides an evaluation framework that simulates the live deployment of a model in production, and a distributed computing backend to run time series models at industrial scale. This library aims to provide engineers and researchers a one-stop solution to rapidly develop models for their specific time series needs and benchmark them across multiple datasets. [ABSTRACT FROM AUTHOR]
Subject terms:
TIME series analysis - DISTRIBUTED computing - MACHINE learning - RESEARCH personnel - MODELS & modelmakingContent provider:
Business Source Premier
Enabling mobile application mashups with Merlion
Conference
|
Proceedings of the Eleventh Workshop on Mobile Computing Systems & Applications. :72-77
Please log in to see more details
Mohomed, Iqbal
Conference
|
Proceedings of the Eleventh Workshop on Mobile Computing Systems & Applications. :72-77
Please log in to see more details
Ulysses by the Merlion
Thumboo, Edwin, 1933-;Thumboo, Edwin, 1933-
Periodical
|
Biotech Financial Reports. Jul2017, Vol. 24 Issue 7, p5-8. 4p.
Please log in to see more details
The article offers information on the grant of Defense Threat Reduction Agency (DTRA) ...
more
Biotech Financial Reports. Jul2017, Vol. 24 Issue 7, p5-8. 4p.
The article offers information on the grant of Defense Threat Reduction Agency (DTRA) Chemical and Biological Defense Program for A MerLion Pharmaceuticals joint project with the Defense Science and Technology Laboratory. It mention that project study the impact of MerLion ’s novel fluoroquinolone finafloxacin for the treatment of infections caused by Burkholderia pseudomallei. It also study the broad spectrum efficacy of finafloxacin against Francisella tularensis and Yersinia pestis.
