ﻻ يوجد ملخص باللغة العربية
Monitoring active volcanos is an ongoing and important task helping to understand and predict volcanic eruptions. In recent years, analysing the acoustic properties of eruptions became more relevant. We present an inexpensive, lightweight, portable, easy to use and modular acoustic data acquisition system for field measurements that can record data with up to 100~kHz. The system is based on a Raspberry Pi 3 B running a custom build bare metal operating system. It connects to an external analog - digital converter with the microphone sensor. A GPS receiver allows the logging of the position and in addition the recording of a very accurate time signal synchronously to the acoustic data. With that, it is possible for multiple modules to effectively work as a single microphone array. The whole system can be build with low cost and demands only minimal technical infrastructure. We demonstrate a possible use of such a microphone array by deploying 20 modules on the active volcano textit{Stromboli} in the Aeolian Islands by Sicily, Italy. We use the collected acoustic data to indentify the sound source position for all recorded eruptions.
Beamforming methods for sound source localization are usually based on free-field Greens functions to model the sound propagation between source and microphone. This assumption is known to be incorrect for many industrial applications and the beamfor
Multimodal learning allows us to leverage information from multiple sources (visual, acoustic and text), similar to our experience of the real world. However, it is currently unclear to what extent auxiliary modalities improve performance over unimod
When deploying a Chinese neural text-to-speech (TTS) synthesis system, one of the challenges is to synthesize Chinese utterances with English phrases or words embedded. This paper looks into the problem in the encoder-decoder framework when only mono
Mosquitoes are the only known vector of malaria, which leads to hundreds of thousands of deaths each year. Understanding the number and location of potential mosquito vectors is of paramount importance to aid the reduction of malaria transmission cas
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the knowledge sh