mlsanityData to 7 Oct 2026

Spatial LibriSpeech: An Augmented Dataset for Spatial Audio Learning

arXiv 2308.09514 ↗First posted 18 Aug 2023cs.SD cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We present Spatial LibriSpeech, a spatial audio dataset with over 650 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 200k+ simulated acoustic conditions across 8k+ synthetic rooms. To demonstrate the utility of our dataset, we train models on four spatial audio tasks, resulting in a median absolute error of 6.60deg on 3D source localization, 0.43m on distance, 90.66ms on T30, and 2.74dB on DRR estimation. We show that the same models generalize well to widely-used evaluation datasets, e.g., obtaining a median absolute error of 12.43deg on 3D source localization on TUT Sound Events 2018, and 157.32ms on T30 estimation on ACE Challenge.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

18 of 41 references.

References · 18

  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  2. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  3. 2018Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networkscited by 84
  4. 2020Sudo rm -rf: Efficient Networks for Universal Audio Source Separationcited by 50
  5. 2018Diversity in Machine Learningcited by 48
  6. 2021A Survey of Sound Source Localization with Deep Learning Methodscited by 45
  7. 2018Building and Evaluation of a Real Room Impulse Response Datasetcited by 43
  8. 2021Interspeech 2021 Deep Noise Suppression Challengecited by 43
  9. 2021EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environmentscited by 29
  10. 2021A Dataset of Dynamic Reverberant Sound Scenes with Directional Interferers for Sound Event Localization and Detectioncited by 20
  11. 2021dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processingcited by 10
  12. 2021Dataset of Spatial Room Impulse Responses in a Variable Acoustics Room for Six Degrees-of-Freedom Rendering and Analysiscited by 9
6 more
  1. 2021PILOT: Introducing Transformers for Probabilistic Sound Event Localizationcited by 7
  2. 2017The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environmentscited by 3
  3. 2021Blind Room Parameter Estimation Using Multiple-Multichannel Speech Recordingscited by 3
  4. 2021A data acquisition setup for data driven acoustic designcited by 3
  5. 2020BIRD: Big Impulse Response Datasetcited by 2
  6. 2020Deep Neural Network based Distance Estimation for Geometry Calibration in Acoustic Sensor Networkscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 1.

6 papers.

  1. 2024Learning Spatially-Aware Language and Audio Embeddingscited by 15
  2. 2024ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Modelcited by 11
  3. 2023Novel-View Acoustic Synthesis from 3D Reconstructed Roomscited by 6
  4. 2025AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMscited by 2
  5. 2024Blind Estimation of Sub-band Acoustic Parameters from Ambisonics Recordings using Spectro-Spatial Covariance Featurescited by 1
  6. 2026RIPPLE: Generating Multi-Channel Phase, Not Recovering Itcited by 0