No abstract

This paper provides an overview of the Speaker Antispoofing Competition organized by Biometric group at Idiap Research Institute for the IEEE International Conference on Biometrics: Theory, Applications, and Systems (BTAS 2016). The competition used AVspoof database, which contains a comprehensive set of presentation attacks, including, (i) direct replay attacks when a genuine data is played back using a laptop and two phones (Samsung Galaxy S4 and iPhone 3G), (ii) synthesized speech replayed with a laptop, and (iii) speech created with a voice conversion algorithm, also replayed with a laptop.The paper states competition goals, describes the database and the evaluation protocol, discusses solutions for spoofing or presentation attack detection submitted by the participants, and presents the results of the evaluation.

Increasing amount of research has shed light on machine perception of audio events, most of which concerns detection and classification tasks. However, human-like perception of audio scenes involves not only detecting and classifying audio sounds, but also summarizing the relationship between different audio events. Comparable research such as image caption has been conducted, yet the audio field is still quite barren. This paper introduces a manually-annotated dataset for audio caption. The purpose is to automatically generate natural sentences for audio scene description and to bridge the gap between machine perception of audio and image. The whole dataset is labelled in Mandarin and we also include translated English annotations. A baseline encoder-decoder model is provided for both English and Mandarin. Similar BLEU scores are derived for both languages: our model can generate understandable and data-related captions based on the dataset.

No abstract

Task 4 of the DCASE2018 challenge demonstrated that substantially more research is needed for a real-world application of sound event detection. Analyzing the challenge results it can be seen that most successful models are biased towards predicting long (e.g., over 5s) clips. This work aims to investigate the performance impact of fixed-sized window median filter post-processing and advocate the use of double thresholding as a more robust and predictable post-processing method. Further, four different temporal subsampling methods within the CRNN framework are proposed: mean-max, α-mean-max, L p -norm and convolutional. We show that for this task subsampling the temporal resolution by a neural network enhances the F1 score as well as its robustness towards short, sporadic sound events. Our best single model achieves 30.1% F1 on the evaluation set and the best fusion model 32.5%, while being robust to event length variations.

Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware features are a possible solution to this problem. Most successful methods in both challenges focus on spoof-aware features, rather than focusing on a powerful classifier. In this paper we present a novel raw waveform based deep model for spoofing detection, which jointly acts as a feature extractor and classifier, thus allowing it to directly classify speech signals. This approach can be considered as an end-to-end classifier, which removes the need for any pre-or post-processing on the data, making training and evaluation a streamlined process, consuming less time than other neural-network based approaches. The experiments on the BTAS2016 dataset show that the system performance is significantly improved by the proposed raw waveform convolutional long short term neural network (CLDNN), from the previous best published 1.26% half total error rate (HTER) to the current 0.82% HTER. Moreover it shows that the proposed system also performs well under the unknown (RE-PH2-PH3,RE-LPPH2-PH3) conditions.

Sound event detection (SED) is the task of tagging the absence or presence of audio events and their corresponding interval within a given audio clip. While SED can be done using supervised machine learning, where training data is fully labeled with access to per event timestamps and duration, our work focuses on weakly-supervised sound event detection (WSSED), where prior knowledge about an event's duration is unavailable. Recent research within the field focuses on improving segment-and event-level localization performance for specific datasets regarding specific evaluation metrics. Specifically, wellperforming event-level localization work requires fully labeled development subsets to obtain event duration estimates, which significantly benefits localization performance. Moreover, wellperforming segment-level localization models output predictions at a coarse-scale (e.g., 1 second), hindering their deployment on datasets containing very short events (< 1 second). This work proposes a duration robust CRNN (CDur) framework, which aims to achieve competitive performance in terms of segmentand event-level localization. In the meantime, this paper proposes a new post-processing strategy named "Triple Threshold" and investigates two data augmentation methods along with a label smoothing method within the scope of WSSED. Event-, Segment-, and Tagging-F1 scores are utilized as primary evaluation metrics. Evaluation of our model is done on three publicly available datasets: Task 4 of the DCASE2017 and 2018 datasets, as well as URBAN-SED. Our model outperforms other approaches on the DCASE2018 and URBAN-SED datasets without requiring prior duration knowledge. In particular, our model is capable of similar performance to strongly-labeled supervised models on the URBAN-SED dataset. Lastly, we run a series of ablation experiments to reveal that without post-processing, our model's localization performance drop is significantly lower compared with other approaches.

No abstract