CRNN-based joint azimuth and elevation localization with the Ambisonics intensity vector - Archive ouverte HAL Access content directly
Conference Papers Year :

CRNN-based joint azimuth and elevation localization with the Ambisonics intensity vector

(1, 2) , (2) , (2) , (1)
1
2

Abstract

We present a source localization system for first-order Ambisonics (FOA) contents based on a stacked convolutional and recurrent neural network (CRNN). We propose to use as input to the CRNN the FOA acoustic intensity vector, which is easy to compute and closely linked to the sound direction of arrival (DoA). The system estimates the DoA of a point source in both azimuth and elevation. We conduct an experimental evaluation in configurations including reverberation, noise, and various speaker w.r.t. microphone orientations. The results show that the proposed architecture and input allow the network to return accurate location estimates in realistic conditions compared to another recent CRNN-based system.
Fichier principal
Vignette du fichier
articleIWAENC.pdf (324.77 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01840453 , version 1 (16-07-2018)

Identifiers

  • HAL Id : hal-01840453 , version 1

Cite

Lauréline Perotin, Romain Serizel, Emmanuel Vincent, Alexandre Guérin. CRNN-based joint azimuth and elevation localization with the Ambisonics intensity vector. IWAENC 2018 - 16th International Workshop on Acoustic Signal Enhancement, Sep 2018, Tokyo, Japan. ⟨hal-01840453⟩
426 View
892 Download

Share

Gmail Facebook Twitter LinkedIn More