Audio signals represent a wide diversity of acoustic events, from background environmental noise to spoken communication. Machine learning models such as neural networks have already been proposed for audio signal modeling, where recurrent structures can take advantage of temporal dependencies. This work aims to study the implementation of several neural network-based systems for speech and music event detection over a collection of 77,937 10-second audio segments (216 h), selected from the Google AudioSet dataset. These segments belong to YouTube videos and have been represented as mel-spectrograms. We propose and compare two approaches. The first one is the training of two different neural networks, one for speech detection and another for music detection. The second approach consists on training a single neural network to tackle both tasks at the same time. The studied architectures include fully connected, convolutional and LSTM (long short-term memory) recurrent networks. Comparative results are provided in terms of classification performance and model complexity. We would like to highlight the performance of convolutional architectures, specially in combination with an LSTM stage. The hybrid convolutional-LSTM models achieve the best overall results (85% accuracy) in the three proposed tasks. Furthermore, a distractor analysis of the results has been carried out in order to identify which events in the ontology are the most harmful for the performance of the models, showing some difficult scenarios for the detection of music and speech.

Sound Event Detection is a task with a rising relevance over the recent years in the field of audio signal processing, due to the creation of specific datasets such as Google AudioSet or DESED (Domestic Environment Sound Event Detection) and the introduction of competitive evaluations like the DCASE Challenge (Detection and Classification of Acoustic Scenes and Events). The different categories of acoustic events can present diverse temporal and spectral characteristics. However, most approaches use a fixed time-frequency resolution to represent the audio segments. This work proposes a multi-resolution analysis for feature extraction in Sound Event Detection, hypothesizing that different resolutions can be more adequate for the detection of different sound event categories, and that combining the information provided by multiple resolutions could improve the performance of Sound Event Detection systems. Experiments are carried out over the DESED dataset in the context of the DCASE 2020 Challenge, concluding that the combination of up to 5 resolutions allows a neural network-based system to obtain better results than single-resolution models in terms of event-based F1-score in every event category and in terms of PSDS (Polyphonic Sound Detection Score). Furthermore, we analyze the impact of score thresholding in the computation of F1-score results, finding that the standard value of 0.5 is suboptimal and proposing an alternative strategy based in the use of a specific threshold for each event category, which obtains further improvements in performance.

Replay attacks, where an impostor replays a genuine user utterance, are a major vulnerability of speaker verification systems. Two highly likely scenarios for replay attacks are either hidden recording of actual spoken access trials, or reusing previous genuine recordings in case of fraudulent access to transmission channels or storage devices. In both scenarios, an audio fingerprint-based approach comparing any access trial with all previous recordings from the claimed speaker perfectly fits the task of replay attack detection. However, ASVspoof 2017 rules did not allow the use of the original RedDots audio files (spoofed trials are replayed versions of RedDots), which disabled a fingerprint-based regular participation in the evaluation as those original files are necessary to build the bank of previous-access audio fingerprints. Then, we agreed with the organizers to run and submit on time a parallel fingerprintbased evaluation with exactly the same blind test data with an alternative but realistic (deployable) evaluation scenario. While we obtained an Equal Error Rate of 8.91% detecting replayed versus genuine trials, this result is not comparable for ranking purposes with those from actual participants in the Challenge as we used the original RedDots files. However, it provides insight into the potential and complementarity of audio fingerprinting, especially for high audio-quality attacks where state-of-the-art acoustic antispoofing systems show poor performance (the best ASVspoof 2017 system with global EER of 6.73% degraded to about 25% in condition C6 of high-quality replays), while our fingerprint-based antispoofer obtains an EER of 0.0% for the high-quality replays in condition C6, showing the complementarity of acoustic antispoofers for low-mid quality replays and fingerprint-based ones for mid-high quality replays.

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

The Sound Event Detection task aims to determine the temporal locations of acoustic events in audio clips. In recent years, the relevance of this field is rising due to the introduction of datasets such as Google AudioSet or DESED (Domestic Environment Sound Event Detection) and competitive evaluations like the DCASE Challenge (Detection and Classification of Acoustic Scenes and Events). In this paper, we analyze the performance of Sound Event Detection systems under diverse artificial acoustic conditions such as high- or low-pass filtering and clipping or dynamic range compression, as well as under an scenario of high overlap between events. For this purpose, the audio was obtained from the Evaluation subset of the DESED dataset, whereas the systems were trained in the context of the DCASE Challenge 2020 Task 4. Our systems are based upon the challenge baseline, which consists of a Convolutional-Recurrent Neural Network trained using the Mean Teacher method, and they employ a multiresolution approach which is able to improve the Sound Event Detection performance through the use of several resolutions during the extraction of Mel-spectrogram features. We provide insights on the benefits of this multiresolution approach in different acoustic settings, and compare the performance of the single-resolution systems in the aforementioned scenarios when using different resolutions. Furthermore, we complement the analysis of the performance in the high-overlap scenario by assessing the degree of overlap of each event category in sound event detection datasets.