*.wav

The data are the original data of UAV sound source localization by ODAS system consisting of 12-channel spherical microphone array and circular MEMS microphone array of dual system. The data contains four different types of UAV sound sources, and the UAV sound sources in different frequency bands are used to locate the sound sources of multiple UAVs.

This dataset contains audio recordings sourced from more than 57 TV shows provided by the Saudi Broadcasting Authority. The total number of hours published for these recordings is ~667 hours. The recordings are in Arabic, the majority are in Saudi dialects, and some are in other dialects. To enhance the usage of SADA, the dataset is split into training, validation, and testing sets. Each of validation and testing sets is around 10 hours in audio segments length while training set is 418 hours.

Introduced here is the Extended-Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition (ELAD-SVDSR), a resource designed to advance research in synthetic voice (DeepFake) detection and automatic speaker recognition (ASR). It features around 45-minute audio recordings from 36 participants, each of whom read aloud different newspaper articles during controlled sessions, captured with five different high-quality microphones. Synthetic voices generated from 20 subjects of this dataset using open-source and commercial software are also included.

The limited availability of Guitar notes datasets hinders the training of any artificial intelligence model in this field. TaptoTab dataset aims to fill this gap by providing a collection of notes recordings. This dataset is collected as part of an honours project at the Faculty of Computer and Information Sciences, Ain Shams University. The dataset is composed of audio data that has been self-collected, focusing on capturing a comprehensive range of guitar notes. The dataset consists of recordings of guitar notes played on each of the six strings, covering up to the 12th fret.

Insulation fault detection in rotating machinery using Partial Discharge (PD) has been a hot research topic over the last decades. In recent years, attention has also been paid to low voltage machines, following the advent of wide bandgap semiconductor devices. This paper presents a low-cost, modular, and full-digital PD monitoring device, particularly suitable for deployment in large industrial plants. The proposed innovative solution allows us to implement a monitoring network, ensuring complete coverage in large industrial plants and continuous monitoring of critical machinery.

Active noise control (ANC) aims at reducing a noise source at a listening point by destructive interference with a reversed phase noise emitted by one or more controlling devices. These data are from an active vibration control (AVC) system applied to a wall of the metal box of a cogeneration plant. It makes use of electro-dynamic shakers as controllers and accelerometers as error and reference signals. The algorithm employed for generating the cancelling signals is a single-reference, single-input multiple-output (MIMO) Filtered-X Normalized Least Mean Square (FxNLMS).

JVNV is a Japanese emotional speech corpus with verbal content and nonverbal vocalizations whose scripts are generated by a large-scale language model.

Existing emotional speech corpora lack not only proper emotional scripts but also nonverbal vocalizations (NVs) that are essential expressions in spoken language to express emotions.

We propose an automatic script generation method to produce emotional scripts by providing seed words with sentiment polarity and phrases of nonverbal vocalizations to ChatGPT using prompt engineering.