@inproceedings{Christensen2010,
    Author = "Christensen, Heidi and Barker, Jon and Ma, Ning and Green, Phil D.",
    title = "The CHiME corpus: a resource and a challenge for computational hearing in multisource environments.",
    booktitle = "{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association",
    pages = "1918-1921",
    year = "2010",
    publisher = "ISCA",
    abstract = "We present a new corpus designed for noise-robust speech processing research, CHiME. Our goal was to produce material which is both natural (derived from reverberant domestic environments with many simultaneous and unpredictable sound sources) and controlled (providing an enumerated range of SNRs spanning 20 dB). The corpus includes around 40 hours of background recordings from a head and torso simulator positioned in a domestic setting, and a comprehensive set of binaural impulse responses collected in the same environment. These have been used to add target utterances from the Grid speech recognition corpus into the CHiME domestic setting. Data has been mixed in a manner that produces a controlled and yet natural range of SNRs over which speech separation, enhancement and recognition algorithms can be evaluated. The paper motivates the design of the corpus, and describes the collection and post-processing of the data. We also present a set of baseline recognition results."
}

@inproceedings{Foster2015,
    Author = "{Foster}, P. and {Sigtia}, S. and {Krstulovic}, S. and {Barker}, J. and {Plumbley}, M. D.",
    booktitle = "2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)",
    title = "Chime-home: A dataset for sound source recognition in a domestic environment",
    year = "2015",
    volume = "",
    number = "",
    pages = "1-5",
    abstract = "For the task of sound source recognition, we introduce a novel data set based on 6.8 hours of domestic environment audio recordings. We describe our approach of obtaining annotations for the recordings. Further, we quantify agreement between obtained annotations. Finally, we report baseline results for sound source recognition using the obtained dataset. Our annotation approach associates each 4-second excerpt from the audio recordings with multiple labels, based on a set of 7 labels associated with sound sources in the acoustic environment. With the aid of 3 human annotators, we obtain 3 sets of multi-label annotations, for 4378 4-second audio excerpts. We evaluate agreement between annotators by computing Jaccard indices between sets of label assignments. Observing varying levels of agreement across labels, with a view to obtaining a representation of `ground truth' in annotations, we refine our dataset to obtain a set of multi-label annotations for 1946 audio excerpts. For the set of 1946 annotated audio excerpts, we predict binary label assignments using Gaussian mixture models estimated on MFCCs. Evaluated using the area under receiver operating characteristic curves, across considered labels we observe performance scores in the range 0.76 to 0.98.",
    keywords = "acoustic radiators;audio recording;audio signal processing;Gaussian processes;mixture models;sensitivity analysis;sound source recognition;domestic environment audio recordings;acoustic environment;multilabel annotation;Jaccard indices computation;binary label assignment prediction;Gaussian mixture model;MFCC;receiver operating characteristic curve;Acoustics;Speech;Speech processing;Audio recording;Conferences;Speech recognition;Computational Auditory Scene analysis;Sound Source Recognition;Datasets",
    doi = "10.1109/WASPAA.2015.7336899",
    issn = "",
    month = "Oct"
}

@book{Murphy2012,
    Author = "Murphy, Kevin P.",
    title = "Machine learning : a probabilistic perspective",
    address = "Cambridge, Mass. [u.a.]",
    description = "Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series): Kevin P. Murphy: 9780262018029: Amazon.com: Books",
    isbn = "9780262018029 0262018020",
    keywords = "Machine learning",
    publisher = "MIT Press",
    year = "2013",
    url = "https://www.amazon.com/Machine-Learning-Probabilistic-Perspective-Computation/dp/0262018020/ref=sr\_1\_2?ie=UTF8\&qid=1336857747\&sr=8-2"
}

@article{Mesaros2018_TASLP,
    author = "Mesaros, A. and Heittola, T. and Benetos, E. and Foster, P. and Lagrange, M. and Virtanen, T. and Plumbley, M. D.",
    journal = "IEEE/ACM Transactions on Audio, Speech, and Language Processing",
    title = "Detection and Classification of Acoustic Scenes and Events: Outcome of the {DCASE} 2016 Challenge",
    year = "2018",
    volume = "26",
    number = "2",
    pages = "379--393",
    abstract = "Public evaluation campaigns and datasets promote active development in target research areas, allowing direct comparison of algorithms. The second edition of the challenge on detection and classification of acoustic scenes and events (DCASE 2016) has offered such an opportunity for development of the state-of-the-art methods, and succeeded in drawing together a large number of participants from academic and industrial backgrounds. In this paper, we report on the tasks and outcomes of the DCASE 2016 challenge. The challenge comprised four tasks: acoustic scene classification, sound event detection in synthetic audio, sound event detection in real-life audio, and domestic audio tagging. We present each task in detail and analyze the submitted systems in terms of design and performance. We observe the emergence of deep learning as the most popular classification method, replacing the traditional approaches based on Gaussian mixture models and support vector machines. By contrast, feature representations have not changed substantially throughout the years, as mel frequency-based representations predominate in all tasks. The datasets created for and used in DCASE 2016 are publicly available and are a valuable resource for further research.",
    keywords = "Acoustics;Event detection;Hidden Markov models;Speech;Speech processing;Tagging;Acoustic scene classification;audio datasets;pattern recognition;sound event detection",
    doi = "10.1109/TASLP.2017.2778423",
    issn = "2329-9290",
    month = "Feb"
}