Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Di Carlo, Diego, Nugraha, Aditya Arie, Fontaine, Mathieu, Yoshii, Kazuyoshi
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913249284325376
author Di Carlo, Diego
Nugraha, Aditya Arie
Fontaine, Mathieu
Fontaine, Mathieu
Yoshii, Kazuyoshi
author_facet Di Carlo, Diego
Nugraha, Aditya Arie
Fontaine, Mathieu
Fontaine, Mathieu
Yoshii, Kazuyoshi
contents We address the problem of accurately interpolating measured anechoic steering vectors with a deep learning framework called the neural field. This task plays a pivotal role in reducing the resource-intensive measurements required for precise sound source separation and localization, essential as the front-end of speech recognition. Classical approaches to interpolation rely on linear weighting of nearby measurements in space on a fixed, discrete set of frequencies. Drawing inspiration from the success of neural fields for novel view synthesis in computer vision, we introduce the neural steerer, a continuous complex-valued function that takes both frequency and direction as input and produces the corresponding steering vector. Importantly, it incorporates inter-channel phase difference information and a regularization term enforcing filter causality, essential for accurate steering vector modeling. Our experiments, conducted using a dataset of real measured steering vectors, demonstrate the effectiveness of our resolution-free model in interpolating such measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2305_04447
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions
Di Carlo, Diego
Nugraha, Aditya Arie
Fontaine, Mathieu
Fontaine, Mathieu
Yoshii, Kazuyoshi
Audio and Speech Processing
Sound
We address the problem of accurately interpolating measured anechoic steering vectors with a deep learning framework called the neural field. This task plays a pivotal role in reducing the resource-intensive measurements required for precise sound source separation and localization, essential as the front-end of speech recognition. Classical approaches to interpolation rely on linear weighting of nearby measurements in space on a fixed, discrete set of frequencies. Drawing inspiration from the success of neural fields for novel view synthesis in computer vision, we introduce the neural steerer, a continuous complex-valued function that takes both frequency and direction as input and produces the corresponding steering vector. Importantly, it incorporates inter-channel phase difference information and a regularization term enforcing filter causality, essential for accurate steering vector modeling. Our experiments, conducted using a dataset of real measured steering vectors, demonstrate the effectiveness of our resolution-free model in interpolating such measurements.
title Neural Steerer: Novel Steering Vector Synthesis with a Causal Neural Field over Frequency and Source Positions
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2305.04447