High-resolution speaker counting in reverberant rooms using CRNN with Ambisonics features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

High-resolution speaker counting in reverberant rooms using CRNN with Ambisonics features

Résumé

Speaker counting is the task of estimating the number of people that are simultaneously speaking in an audio recording. For several audio processing tasks such as speaker diarization, separation, localization and tracking, knowing the number of speakers at each timestep is a prerequisite, or at least it can be a strong advantage, in addition to enabling a low latency processing. For that purpose, we address the speaker counting problem with a multichannel convolutional recurrent neural network which produces an estimation at a short-term frame resolution. We trained the network to predict up to 5 concurrent speakers in a multichannel mixture, with simulated data including many different conditions in terms of source and microphone positions, reverberation, and noise. The network can predict the number of speakers with good accuracy at frame resolution.
Fichier principal
Vignette du fichier
eusipco2020.pdf (374.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03537323 , version 1 (20-01-2022)

Identifiants

Citer

Pierre-Amaury Grumiaux, Srdan Kitic, Laurent Girin, Alexandre Guerin. High-resolution speaker counting in reverberant rooms using CRNN with Ambisonics features. EUSIPCO 2020 - 28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam, Netherlands. pp.71-75, ⟨10.23919/Eusipco47968.2020.9287637⟩. ⟨hal-03537323⟩
27 Consultations
46 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More