Semantic audio analysis has become a fundamental task in modern audio applications, making the improvement and optimization of classification algorithms a necessity. Standard frame-based audio classification methods have been optimized, and modern approaches introduce engineering methodologies that capture the temporal dependency between successive feature observations, following the process of temporal feature integration. Moreover, the deployment of the convolutional neural networks defined...

The current paper focuses on the development of an enhanced Mobile Journalism (MoJo) model for soundscape heritage crowdsourcing, data-driven storytelling, and management in the era of big data and the semantic web. Soundscapes and environmental sound semantics have a great impact on cultural heritage, also affecting the quality of human life, from multiple perspectives. In this view, context- and location-aware mobile services can be combined with state-of-the-art machine and deep learning approaches to offer multilevel semantic analysis monitoring of sound-related heritage. The targeted utilities can offer new insights toward sustainable growth of both urban and rural areas. Much emphasis is also put on the multimodal preservation and auralization of special soundscape areas and open ancient theaters with remarkable acoustic behavior, representing important cultural artifacts. For this purpose, a pervasive computing architecture is deployed and investigated, utilizing both client- and cloud-wise semantic analysis services, to implement and evaluate the envisioned MoJo methodology. Elaborating on previous/baseline MoJo tools, research hypotheses and questions are stated and put to test as part of the human-centered application design and development process. In this setting, primary algorithmic backend services on sound semantics are implemented and thoroughly validated, providing a convincing proof of concept of the proposed model.

In this study, we aim to learn highly descriptive representations for a wide set of machinery sounds and exploit this knowledge to perform condition monitoring of mechanical equipment. We propose a comprehensive feature learning approach that operates on raw audio, by supervising the formation of salient audio embeddings in latent states of a deep temporal convolutional neural network. By fusing the supervised feature learning approach with an unsupervised deep one-class neural network, we are able to model the characteristics of each source and implicitly detect anomalies in different operational states of industrial machines. Moreover, we enable the exploitation of spatial audio information in the learning process, by formulating a novel front-end processing strategy for circular microphone arrays. Experimental results on the MIMII dataset demonstrate the effectiveness of the proposed method, reaching a state-of-the-art mean AUC score of 91.0%. Anomaly detection performance is significantly improved by incorporating multi-channel audio data in the feature extraction process, as well as training the convolutional neural network on the spatially invariant front-end. Finally, the proposed semi-supervised approach allows the concise modeling of normal machine conditions and accurately detects system anomalies, compared to existing anomaly detection methods.

Understanding speech in noisy environments is a challenging task, especially in communication situations with several competing speakers. Despite their ongoing improvement, assistive listening devices and speech processing approaches still do not perform well enough in noisy multi-talker environments, as they may fail to restore the intelligibility of a speaker of interest among competing sound sources. In this study, a quasi-causal deep learning algorithm was developed that can extract the voice of a target speaker, as indicated by a short enrollment utterance, from a mixture of multiple concurrent speakers in background noise. Objective evaluation with computational metrics demonstrated that the speaker-informed algorithm successfully extracts the target speaker from noisy multi-talker mixtures. This was achieved using a single algorithm that generalized to unseen speakers, different numbers of speakers and relative speaker levels, and different speech corpora. Double-blind sentence recognition tests on mixtures of one, two, and three speakers in restaurant noise were conducted with listeners with normal hearing and listeners with hearing loss. Results indicated significant intelligibility improvements with the speaker-informed algorithm of 17% and 31% for people without and with hearing loss, respectively. In conclusion, it was demonstrated that deep learning-based speaker extraction can enhance speech intelligibility in noisy multi-talker environments where uninformed speech enhancement methods fail.

Modern feature-based methodologies in semantic audio applications attempt to capture the temporal dependency of successive feature observations, which form the so-called texture windows. This paper proposes an enhancement of this type of processing, known as temporal feature integration, by employing and testing alternative deployable strategies. Specifically, data are fitted through commonly used statistical principles, estimating the parameters of a given probability density function that...

Objective: To develop and evaluate a software application capable of conducting Pure-Tone Audiometry tests in clinical practice. Design: We designed and developed a mobile software application for iPad devices that performs Pure-Tone Audiometry according to ANSI and IEC standards. The application is proposed to be operated by a trained audiologist inside a sound booth. No extra equipment is required. Hence, it updates the procedure by showing the versatility of the proposed system. Particularly, it provides manual and automated measurement, including air- and bone-conduction audiometry. Study sample: Twenty-nine participants-patients of Papageorgiou Hospital, Thessaloniki, Greece were tested, with all degrees of hearing sensitivity. Manual air- and bone-conduction Pure-Tone Audiometry was conducted inside a sound booth. Participants were tested with conventional audiometry and the audiometric application, in order to validate the tablet-based audiometer for measuring hearing thresholds. Results: The majority (90.9%) of air-conduction estimated hearing thresholds and (90.8%) of air-bone gaps were within 5 dB, compared to results obtained by conventional audiometry. Thus, threshold differences were not significant. Conclusions: The proposed audiometer is a reliable and valid tool for hearing assessment. Owing to certain limitations, mobile devices can provide a feasible substitute for conventional audiometry in clinical practice.