We present Spatial LibriSpeech, a spatial audio dataset with over 570 hours of 19-channel audio, first-order ambisonics, and optional distractor noise. Spatial LibriSpeech is designed for machine learning model training, and it includes labels for source position, speaking direction, room acoustics and geometry. Spatial LibriSpeech is generated by augmenting LibriSpeech samples with >220k simulated acoustic conditions across >8k synthetic rooms. To demonstrate the utility of our dataset, we train models on four fundamental spatial audio tasks, resulting in a median absolute error of 6.60° on 3D source localization, 0.43m on distance, 90.66ms on T30, and 2.74dB on direct-to-reverberant ratio estimation. We show that the same models transfer to widely-used evaluation datasets, obtaining, for instance, a median absolute error of 12.43° on 3D source localization on TUT Sound Events 2018, and 157.32ms on T30 estimation on ACE Challenge.

Related readings and updates.

FERRET: Refer and Ground Anything Anywhere at Any Granularity

Multimodal Large Language Models exhibit impressive vision-language capabilities but often struggle with fine-grained spatial understanding. We introduce FERRET, a novel MLLM capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions. A hybrid region representation is proposed to marry discrete coordinates with continuous visual features, endowing versatile…
See paper details

Interspeech 2023

Apple sponsored the Interspeech Conference, which took place in person from August 20 to 24 in Dublin, Ireland. Interspeech is a conference on the science and technology of spoken language processing. Below was the schedule of Apple-sponsored workshops and events at the conference.

See event details