@inproceedings{Mesaros2016_EUSIPCO,
    author = "Mesaros, Annamaria and Heittola, Toni and Virtanen, Tuomas",
    title = "{TUT} Database for Acoustic Scene Classification and Sound Event Detection",
    abstract = "We introduce TUT Acoustic Scenes 2016 database for environmental sound research, consisting ofbinaural recordings from 15 different acoustic environments. A subset of this database, called TUT Sound Events 2016, contains annotations for individual sound events, specifically created for sound event detection. TUT Sound Events 2016 consists of residential area and home environments, and is manually annotated to mark onset, offset and label of sound events. In this paper we present the recording and annotation procedure, the database content, a recommended cross-validation setup and performance of supervised acoustic scene classification system and event detection baseline system using mel frequency cepstral coefficients and Gaussian mixture models. The database is publicly released to provide support for algorithm development and common ground for comparison of different techniques.",
    year = "2016",
    address = "Budapest, Hungary",
    booktitle = "24th European Signal Processing Conference 2016 (EUSIPCO 2016)"
}

@inproceedings{DCASE2017challenge,
    Author = "Mesaros, A. and Heittola, T. and Diment, A. and Elizalde, B. and Shah, A. and Vincent, E. and Raj, B. and Virtanen, T.",
    title = "{DCASE} 2017 Challenge Setup: Tasks, Datasets and Baseline System",
    booktitle = "Proceedings of the Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017)",
    year = "2017",
    month = "November",
    pages = "85--92",
    abstract = "DCASE 2017 Challenge consists of four tasks: acoustic scene classification, detection of rare sound events, sound event detection in real-life audio, and large-scale weakly supervised sound event detection for smart cars. This paper presents the setup of these tasks: task definition, dataset, experimental setup, and baseline system results on the development dataset. The baseline systems for all tasks rely on the same implementation using multilayer perceptron and log mel-energies, but differ in the structure of the output layer and the decision making process, as well as the evaluation of system output using task specific metrics.",
    keywords = "Sound scene analysis, Acoustic scene classification, Sound event detection, Audio tagging, Rare sound events"
}

@inproceedings{Mesaros2016_EUSIPCO,
    author = "Mesaros, Annamaria and Heittola, Toni and Virtanen, Tuomas",
    title = "{TUT} Database for Acoustic Scene Classification and Sound Event Detection",
    abstract = "We introduce TUT Acoustic Scenes 2016 database for environmental sound research, consisting ofbinaural recordings from 15 different acoustic environments. A subset of this database, called TUT Sound Events 2016, contains annotations for individual sound events, specifically created for sound event detection. TUT Sound Events 2016 consists of residential area and home environments, and is manually annotated to mark onset, offset and label of sound events. In this paper we present the recording and annotation procedure, the database content, a recommended cross-validation setup and performance of supervised acoustic scene classification system and event detection baseline system using mel frequency cepstral coefficients and Gaussian mixture models. The database is publicly released to provide support for algorithm development and common ground for comparison of different techniques.",
    year = "2016",
    address = "Budapest, Hungary",
    booktitle = "24th European Signal Processing Conference 2016 (EUSIPCO 2016)"
}

@article{Mesaros2016_MDPI,
    author = "Mesaros, Annamaria and Heittola, Toni and Virtanen, Tuomas",
    title = "Metrics for Polyphonic Sound Event Detection",
    journal = "Applied Sciences",
    volume = "6",
    year = "2016",
    number = "6",
    pages = "162",
    url = "http://www.mdpi.com/2076-3417/6/6/162",
    issn = "2076-3417",
    abstract = "This paper presents and discusses various metrics proposed for evaluation of polyphonic sound event detection systems used in realistic situations where there are typically multiple sound sources active simultaneously. The system output in this case contains overlapping events, marked as multiple sounds detected as being active at the same time. The polyphonic system output requires a suitable procedure for evaluation against a reference. Metrics from neighboring fields such as speech recognition and speaker diarization can be used, but they need to be partially redefined to deal with the overlapping events. We present a review of the most common metrics in the field and the way they are adapted and interpreted in the polyphonic case. We discuss segment-based and event-based definitions of each metric and explain the consequences of instance-based and class-based averaging using a case study. In parallel, we provide a toolbox containing implementations of presented metrics.",
    doi = "10.3390/app6060162"
}