, Cascade: a cascade approach where the echo cancellation filter H(f ), the dereverberation filter G(f ) and the Wiener postfilter W se (n, f ) are estimated and applied one after another. Echo cancellation relies on SpeexDSP 1 , which implements Valin's adaptive approach and is particularly suitable for time-varying conditions [11]. Dereverberation relies on our implementation of WPE [2, 6]. The multichannel Wiener postfilter is computed using our implementation of Nugraha, Togami : our implementation of Togami et al.'s approach, vol.2

, NN-parallel : the variant of NN-joint where the echo cancellation filter H(f ) and the dereverberation filter G(f ) are applied in parallel as Togami et al.'s approach

, NN-cascade: the variant of Cascade where the echo cancellation filter H(f ) is estimated using the NN-supported approach similar to NN-joint (see Section 6) instead of Valin's adaptive approach. As WPE dereverberates similarly to its NN-supported counterpart in the multichannel case [16], NN-cascade corresponds to a cascade variant of NN-joint which estimates each filter separately using NN-supported optimization algorithms

G. Carbajal, R. Serizel, E. Vincent, and E. Humbert, Joint DNN-based multichannel reduction of echo, reverberation and noise, Speech, and Language Processing

T. Nakatani, T. Yoshioka, K. Kinoshita, M. Miyoshi, and B. H. Juang, Speech dereverberation based on variance-normalized delayed linear prediction, IEEE Transactions on Audio, Speech, and Language Processing, vol.18, issue.7, pp.1717-1731, 2010.

T. Yoshioka, T. Nakatani, M. Miyoshi, and H. G. Okuno, Blind separation and dereverberation of speech mixtures by joint optimization, IEEE Transactions on Audio, Speech, and Language Processing, vol.19, issue.1, pp.69-84, 2011.

A. A. Nugraha, A. Liutkus, and E. Vincent, Multichannel audio source separation with deep neural networks, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.24, issue.9, pp.1652-1664, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01163369

A. Ozerov and C. Févotte, Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation, IEEE Transactions on Audio, Speech, and Language Processing, vol.18, issue.3, pp.550-563, 2010.

T. Yoshioka and T. Nakatani, Generalization of multi-channel linear prediction methods for blind MIMO impulse response shortening, IEEE Transactions on Audio, Speech, and Language Processing, vol.20, issue.10, pp.2707-2720, 2012.

N. Q. Duong, E. Vincent, and R. Gribonval, Under-determined reverberant audio source separation using a full-rank spatial covariance model, IEEE Transactions on Audio, Speech, and Language Processing, vol.18, issue.7, pp.1830-1840, 2010.
URL : https://hal.archives-ouvertes.fr/inria-00435807

A. A. Nugraha, A. Liutkus, and E. Vincent, Multichannel music separation with deep neural networks, Proc. EUSIPCO, pp.1748-1752, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01334614

A. Liutkus, D. Fitzgerald, and Z. Rafii, Scalable audio separation with light kernel additive modelling, Proc. ICASSP, pp.76-80, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01114890

G. Carbajal, R. Serizel, E. Vincent, and E. Humbert, Joint DNN-based multichannel reduction of echo, reverberation and noise: Supporting document, Inria, 2019.

J. M. Valin, On adjusting the learning rate in frequency domain echo cancellation with double-talk, IEEE Transactions on Audio, Speech, and Language Processing, vol.15, issue.3, pp.1030-1034, 2007.

G. Carbajal, R. Serizel, E. Vincent, and E. Humbert, Multiple-input neural network-based residual echo suppression, Proc. ICASSP, pp.231-235, 2018.
URL : https://hal.archives-ouvertes.fr/hal-01723630

E. Vincent and D. R. Campbell, Roomsimove, 2008.

J. L. Roux, S. Wisdom, H. Erdogan, and J. R. Hershey, SDR -half-baked or well done, Proc. ICASSP, pp.626-630, 2019.

M. Togami and Y. Kawaguchi, Simultaneous optimization of acoustic echo reduction, speech dereverberation, and noise reduction against mutual interference, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.22, issue.11, pp.1612-1623, 2014.

K. Kinoshita, M. Delcroix, H. Kwon, T. Mori, and T. Nakatani, Neural network-based spectrum estimation for online WPE dereverberation, pp.384-388, 2017.