Category: Seminars

Sep 01

Upcoming team seminars

Continue reading »

Jun 29

Black-box Optimization of Deep Neural Networks for Acoustic Modeling

Speaker: Aman Zaid Berhe Date: June 29, 2017 Abstract: Deep neural networks are now the state-of-the-art in acoustic modeling for automatic speech recognition. The allow obtaining robust and high accuracy acoustic models. However, these models have a lot of hyper-parameters. Hyper-parameters optimization is very tedious yet essential tasks to successfully train very deep neural networks. We …

Continue reading »

Jun 22

HRTF range extrapolation by spherical harmonics decomposition

Speaker: Lauréline Perotin Date: June 22, 2017 Abstract: In order to locate sound in space, to know from which direction it comes from but also from how far away, our brain analyses all the distortions applied the soundwave from its (estimated) origin to our eardrums. Those reflections, diffractions and other propagation-related transformations are contained in the …

Continue reading »

Jun 15

An Extended Experimental Investigation of DNN Uncertainty Propagation with Uncertainty Related Features for Noise Robust ASR

Speaker: Karan Nathwani (post-doctoral fellow) Date: June 15, 2017 Abstract: Recently, the idea of estimating the uncertainty about the features obtained after speech enhancement and propagating it to dynamically adapt deep neural network (DNN) based acoustic models has raised some interest. However, the results in the literature were reported on simulated noisy datasets for a limited variety …

Continue reading »

May 18

Robust Online Direction of Arrival Estimation using Spherical Arrays

Speaker: V. Vishnu Vardan Varanasi Date: May 18, 2017 Abstract: DOA Estimation is a challenging task especially in presence of noise and reverberation. Various applications of acoustic source localization include Distant Automatic Speech Recognition, Music Information Retrieval etc. Spherical Microphone Array(SMA) captures spherical variation of acoustic field with spherical harmonics. A wide range of DOA estimation algorithms …

Continue reading »

May 11

Explaining the parameterized Wiener filter with alpha-stable processes

Speaker: Mathieu Fontaine Date: May 11, 2017 Abstract: We introduce a new method for single-channel denoising that sheds new light on classical early developments on this topic that occurred in the 70’s and 80’s with Wiener filtering and spectral subtraction. Operating both in the short-time Fourier transform domain, these methods consist in estimating the power spectral …

Continue reading »

Apr 06

Articulatory speech synthesis from static context-aware articulatory targets

Speaker: Anastasiia Tsukanova Date: April 6, 2017 Abstract: In this talk I will present my work that has been carried out in the domain of articulatory speech synthesis — that is, synthesizing speech through simultaneous control over the articulators (the jaw, the tongue, the lips, the velum, the larynx and the epiglottis) and the source. It …

Continue reading »

Mar 16

Automatic analysis of user’s social cues during mediated communication

Speaker: Nathan Libermann Date: March 16, 2017 Abstract: In this talk I will present the results of my master internship. I propose to explore the social cues expressed by a user during a mediated communication either with an embodied conversational agent or with another human. For this purpose, I have exploited a machine learning method to …

Continue reading »

Feb 09

Supervised group nonnegative matrix factorisation with similarity constraints and applications to speaker identification

Speaker: Romain Serizel Date: February 9, 2017 Abstract: This paper presents supervised feature learning approaches for speaker identification that rely on nonnegative matrix factorisation. Recent studies have shown that group nonnegative matrix factorisation and task-driven supervised dictionary learning can help performing effective feature learning for audio classification problems. This paper proposes to integrate a recent method …

Continue reading »

Jan 16

Environmental low-rank multiway data mining

Speaker: Jérémy E. Cohen (Université de Mons) Date: January 16, 2017