HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information

# Apprentissage profond pour le rehaussement de la parole dans les antennes acoustiques ad-hoc

1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : More and more devices we use in our daily life are embedded with one or more microphones so that they can be voice controlled. Put together, these devices can form a so-called ad-hoc microphone array (AHMA). A speech enhancement step is often applied on the recorded signals to optimise the execution of the voice commands. To this effect, AHMAs are of high interest because of their flexible usage, their wide spatial coverage and the diversity of their recordings. However, it is challenging to exploit the potential of mbox{AHMAs} because devices that compose them may move and have a limited power and bandwidth capacity. Because of these limits, the speech enhancement solutions deployed in classic'' microphone arrays, relying on a fusion center and high processing loads, cannot be afforded.This thesis combines the modelling power of deep neural networks (DNNs) with the flexibility of use of AHMAs. To this end, we introduce a distributed speech enhancement system, which does not rely on a fusion center. So-called compressed signals are sent among the nodes and convey the spatial information recorded by the whole AHMA, while reducing the bandwidth requirements. DNNs are used to estimate the coefficients of a multichannel Wiener filter. We conduct an empirical analysis of this sytem, both on synthesized and real data, in order to validate its efficiency and to highlight the benefits of jointly using DNNs and distributed speech enhancement algorithms. We show that our system performs comparatively well compared with a state-of-the-art solution, while being more flexible and significantly reducing the computation cost.Besides, we develop our solution to adapt it to the typical usage conditions of mbox{AHMAs}. We study its behaviour when the number of devices in the AHMA varies. We introduce and compare a spatial attention mechanism and a self-attention mechanism. Both mechanisms make our system robust to a varying number of devices. We show that the weights of the self-attention mechanism reveal the utility of the information carried by each signal.We also analyse our system when the signals recorded by different devices are not synchronised. We propose a solution to improve its performance in such conditions by introducing a temporal attention mechanism. We show that this mechanism can help estimating the sampling time offset between the several devices of the AHMA.Lastly, we show that our system is also efficient for source separation. It can efficiently process the spatial information recorded by the whole AHMA in a typical meeting scenario and alleviate the needs of a complex DNN architecture.
Keywords :
Document type :
Theses
Domain :

https://hal.univ-lorraine.fr/tel-03598275
Contributor : Thèses Ul Connect in order to contact the contributor
Submitted on : Friday, March 4, 2022 - 5:41:05 PM
Last modification on : Thursday, May 5, 2022 - 10:01:31 AM

### File

DDOC_T_2021_0277_FURNON.pdf
Files produced by the author(s)

### Identifiers

• HAL Id : tel-03598275, version 1

### Citation

Nicolas Furnon. Apprentissage profond pour le rehaussement de la parole dans les antennes acoustiques ad-hoc. Informatique [cs]. Université de Lorraine, 2021. Français. ⟨NNT : 2021LORR0277⟩. ⟨tel-03598275⟩

Record views