Add to ORKGInternational audienceMy talk will focus on robustness to background noise in distant-microphone speech recordings. I will introduce deep learning based techniques for speech enhancement and for acoustic modeling of speech. I will then report the results of a study on the impact of environment and microphone mismatches on the recognition accuracy. This study reveals that mismatched training data can sometimes outperform matched data. I will suggest a way to optimize the training set in order to exploit this finding
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Cu...
Distant-speech recognition represents a technology of fundamental importance for future development ...
The introduction of deep neural networks (DNNs) has advanced the performance of automatic speech rec...
International audienceMy talk will focus on robustness to background noise in distant-microphone spe...
Speech enhancement aims to suppress background noise in noisy speech signals in order to improve spe...
Speech enhancement and automatic speech recognition (ASR) are most often evaluated in matched (or mu...
International audienceMulti-microphone signal processing techniques have the potential to greatly im...
Deep learning is an emerging technology that is considered one of the most promising directions for ...
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Com...
The parametric Bayesian Feature Enhancement (BFE) and a data-driven Denoising Autoencoder (DA) both ...
It is well known that the performances of speech recognition systems degrade rapidly as the mismatch...
Despite the significant progress made in the last years, state-of-the-art speech recognition technolo...
Speaker verication is usually performed by comparing the likelihood score of the target speaker mode...
This thesis describes research into effective voice biometrics (speaker recognition) under mismatche...
MEng (Computer and Electronic Engineering), North-West University, Potchefstroom CampusIn this study...
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Cu...
Distant-speech recognition represents a technology of fundamental importance for future development ...
The introduction of deep neural networks (DNNs) has advanced the performance of automatic speech rec...
International audienceMy talk will focus on robustness to background noise in distant-microphone spe...
Speech enhancement aims to suppress background noise in noisy speech signals in order to improve spe...
Speech enhancement and automatic speech recognition (ASR) are most often evaluated in matched (or mu...
International audienceMulti-microphone signal processing techniques have the potential to greatly im...
Deep learning is an emerging technology that is considered one of the most promising directions for ...
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Com...
The parametric Bayesian Feature Enhancement (BFE) and a data-driven Denoising Autoencoder (DA) both ...
It is well known that the performances of speech recognition systems degrade rapidly as the mismatch...
Despite the significant progress made in the last years, state-of-the-art speech recognition technolo...
Speaker verication is usually performed by comparing the likelihood score of the target speaker mode...
This thesis describes research into effective voice biometrics (speaker recognition) under mismatche...
MEng (Computer and Electronic Engineering), North-West University, Potchefstroom CampusIn this study...
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Cu...
Distant-speech recognition represents a technology of fundamental importance for future development ...
The introduction of deep neural networks (DNNs) has advanced the performance of automatic speech rec...