Alexandre Guérin — accepted AI-conference papers

2025

Stereo Downmix in 3GPP IVAS for EVS Compatibility

Takehiro Moriya, Stéphane Ragot, Arnaud Lefort, Alexandre Guérin, Noboru Harada, Ryosuke Sugiura +1

ICASSP 2025accepted

The 3GPP IVAS codec specifies an EVS-compatible stereo downmix as one of the key functionalities. This paper describes how this novel active downmix scheme has been devised to achieve high and stable quality from stereo input to EVS encoder/decoder with no additional algorithmic delay. An example of…

Cited by 0 Source ↗Scholar ↗

2018

Multichannel Speech Separation with Recurrent Neural Networks from High-Order Ambisonics Recordings

Lauréline Perotin, Romain Serizel, Emmanuel Vincent, Alexandre Guérin

ICASSP 2018accepted

We present a source separation system for high-order ambisonics (HOA) contents. We derive a multichannel spatial filter from a mask estimated by a long short-term memory (LSTM) recurrent neural network. We combine one channel of the mixture with the outputs of basic HOA beamformers as inputs to the…

Cited by 43 Source ↗Scholar ↗