Search for: All records

The dataset includes impulse responses recorded from 14 different rooms. Each room has unique acoustic properties, providing a wide range of RT60, clarity, and EDT values. The recordings are in 48kHz, 32bit, mono WAV files. The dataset is organized by room, with each subfolder containing the impulse responses specific to that room, as well as a general layout of each room and plots of acoustic data.This dataset supports Estimating direction of arrival in reverberant environments for wake-word detection using a single structural vibration sensor, published in the Journal of the Acoustical Society of America, Vol. 156, Iss. 4, October, 2024.If you plan to download this dataset, we would appreciate it very much if you could fill out the Google form at https://forms.gle/jnuP2dYRK3CPmXQG6. This will help us understand the usage and impacts of this dataset. Your feedback will also help us improve any future extensions of this work. 

The vibrational response of an elastic panel to incident acoustic waves is determined by the direction-of-arrival (DOA) of the waves relative to the spatial structure of the panel's bending modes. By monitoring the relative modal excitations of a panel immersed in a sound field, the DOA of the source may be inferred. In reverberant environments, early acoustic reflections and the late diffuse acoustic field may obscure the DOA of incoming sound waves. Panel microphones may be especially susceptible to the effects of reverberation due to their large surface areas and long-decaying impulse responses. An investigation into the effect of reverberation on the accuracy of DOA estimation with panel microphones was made by recording wake-word utterances in eight spaces with reverberation times (RT60s) ranging from 0.27 to 3.00 s. The responses were used to train neural networks to estimate the DOA. Within ±5°, DOA estimation reliability was measured at 95.00% in the least reverberant space, decreasing to 78.33% in the most reverberant space, suggesting an inverse relationship between RT60 and DOA accuracy. Experimental results suggest that a system for estimating DOA with panel microphones can generalize to new acoustic environments by cross-training the system with data from multiple spaces with different RT60s. 

This dataset contains a collection of voice commands for a smart speaker, each beginning with the common wake-word "Hey Alexa". The commands cover a range of tasks such as music control, smart home management, information requests, reminders, shopping, entertainment, and communication. The dataset reflects natural language usage from a diverse group of speakers, capturing various phrasings, inflections, and contexts. It includes contributions from both male and female voices and features speakers with different native languages.If you plan to download this dataset, we would appreciate it very much if you could fill out the Google form at https://forms.gle/dixQ4mkZ4xbXtXRDA. This will help us understand the usage and impacts of this dataset. Your feedback will also help us improve any future extensions of this work.