No abstract

No abstract

The Rhodes piano is an electromechanical keyboard instrument, released for the first time in 1946 and subsequently manufactured for at least four decades, reaching an iconic status and being now generally referred to as the electric piano. A few academic works discuss its operating principle and propose different physical modeling strategies; however, the inharmonic modes that characterize the attack transient have not been subject of a dedicated study before. This study addresses this topic by first observing the spectrum at the pickup output, applying a psychoacoustic model to assess perceptual relevance, and then conducts a series of scanning laser Doppler vibrometry (SLDV) experiments on the Rhodes asymmetric tuning fork. This study compares the modes of the Rhodes piano to those of its individual parts, allowing for the extraction of important information regarding role and natural modes. On the basis of this study, numerical experiments are conducted that show the intermodulation of the modes due to the magnetic pickup and allow the tones produced by the Rhodes from the collected data to be closely matched. Finally, this study is able to extract the distribution of the most important modes found on the whole keyboard range of a Rhodes piano, which can be useful for sound synthesis.

It is a well-established practice to build a robust system for sound event detection by training supervised deep learning models on large datasets, but audio data collection and labeling are often challenging and require large amounts of effort. This paper proposes a workflow based on few-shot metric learning for emergency siren detection performed in steps: prototypical networks are trained on publicly available sources or synthetic data in multiple combinations, and at inference time, the best knowledge learned in associating a sound with its class representation is transferred to identify ambulance sirens, given only a few instances for the prototype computation. Performance is evaluated on siren recordings acquired by sensors inside and outside the cabin of an equipped car, investigating the contribution of filtering techniques for background noise reduction. The results show the effectiveness of the proposed approach, achieving AUPRC scores equal to 0.86 and 0.91 in unfiltered and filtered conditions, respectively, outperforming a convolutional baseline model with and without fine-tuning for domain adaptation. Extensive experiments conducted on several recording sensor placements prove that few-shot learning is a reliable technique even in real-world scenarios and gives valuable insights for developing an in-car emergency vehicle detection system.