J
Joonas Nikunen
Researcher at Tampere University of Technology
Publications - 28
Citations - 714
Joonas Nikunen is an academic researcher from Tampere University of Technology. The author has contributed to research in topics: Spectrogram & Non-negative matrix factorization. The author has an hindex of 11, co-authored 28 publications receiving 511 citations. Previous affiliations of Joonas Nikunen include Nokia.
Papers
More filters
Journal ArticleDOI
Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
TL;DR: The proposed convolutional recurrent neural network for joint sound event localization and detection (SELD) of multiple overlapping sound events in three-dimensional (3-D) space is generic and applicable to any array structures, robust to unseen DOA values, reverberation, and low SNR scenarios.
Journal ArticleDOI
Direction of Arrival Based Spatial Covariance Model for Blind Sound Source Separation
Joonas Nikunen,Tuomas Virtanen +1 more
TL;DR: The proposed SCM model is combined with a linear model for magnitudes and the parameter estimation is formulated in a complex-valued non-negative matrix factorization (CNMF) framework and is shown to exceed the performance of existing state of the art separation methods with two sources when evaluated by objective separation quality metrics.
Journal ArticleDOI
Distant speech separation using predicted time-frequency masks from spatial features
Pasi Pertilä,Joonas Nikunen +1 more
TL;DR: The results show improvement in instrumental measure for intelligibility and frequency-weighted SNR over complex-valued non-negative matrix factorization (CNMF) source separation approach, spatial sound source separation, and conventional beamforming methods such as the DSB and minimum variance distortionless response (MVDR).
Journal ArticleDOI
Separation of Moving Sound Sources Using Multichannel NMF and Acoustic Tracking
TL;DR: In this article, a multichannel NMF model with time-varying mixing of the sources denoted by spatial covariance matrices (SCM) is proposed.
Proceedings ArticleDOI
Multichannel audio separation by direction of arrival based spatial covariance model and non-negative matrix factorization
Joonas Nikunen,Tuomas Virtanen +1 more
TL;DR: The proposed model for SCM is parameterized by source direction of arrival (DoA) and its parameters can be optimized to yield a spatially coherent solution over frequencies thus avoiding permutation ambiguity and spatial aliasing.