Category: Seminars

Multichannel audio source separation with deep neural networks

Speaker: Aditya Arie Nugraha (PhD student) Date: November 26, 2015 Abstract: Many studies have shown that the use of deep neural network (DNN) for audio source separation is extremely promising. However, most studies addressed the problem of single-channel source separation and existing literature lacks a framework to exploit DNN for multichannel audio source separation. In this talk, …

Continue reading

Processing Arabic dialects: scientific and strategic challenges

Speaker: Kamel Smaili (SMarT team) Date: October 14, 2015

Acoustics of open-plan offices

Speaker: Patrick Chevret (INRS) Date: October 1, 2015

Knowledge transfer session on deep learning

Speakers: Imran Sheikh (PhD student) and Aditya Arie Nugraha (PhD student) Date: September 17, 2015 Abstract: This talk will give an overview of the topics covered in the deep learning summer school at Denmark Technical University and the tutorial on deep learning at Interspeech 2015. It will be a quick and informal introduction to several concepts in …

Continue reading

Mapping of a sound environment by a mobile robot

Speaker: Van Quan Nguyen (PhD student) Date: September 10, 2015 Abstract: The research will focus on controlling the robot in order to localize as quickly as possible the position of multiple sound sources with different characteristics in real time and updating the map of this dynamic sound environment while the robot moves. In the talk, I will talk about …

Continue reading

Acoustic control of wind farms

Speaker: Baldwin Dumortier (PhD student) Date: September 3, 2015 Abstract: Wind energy is by far the most used renewable energy in the world.  It is a source of noise pollution and noise regulation of wind turbines has become compulsory.  However,  control strategies are not optimal. Indeed, there are several main problems: there is an issue about measurement of the noise pollution criteria; …

Continue reading

An overview of research activities at PERCEPTION team

Speaker: Laurent Girin (Professor with Grenoble INP and a member of GIPSA-lab and the PERCEPTION team) Date: June 18, 2015 Summary: Laurent Girin presented an overview of research activities at PERCEPTION team whose research axes are computer vision, auditory signal processing and scene analysis, machine learning, and robotics.

Predicting frame-level information from song-level labels

Speaker: Jen-Yu Liu (Visiting scientist; National University of Taiwan and Academica Sinica, Taiwan) Date: June 4, 2015 Abstract: In music information retrieval, we often want to know the frame-level labels. For example, we may want to know where the guitar play is in a song or we may want to know where the male voice …

Continue reading

Pitch based source separation techniques and distant speech recognition

Juan Cordovilla (post-doc, projet voiceHome) Date: May 21st 2015 Abstract: In this presentation I will talk about different topics of my research career basically related to the area of Robust Automatic Speech Recognition (ASR). 1) Asymmetric windows for spectral estimation. 2) The use of the pitch to estimate: the noise (tunneling techniques), the clean signal …

Continue reading