Deep learning for environmentally robust speech recognition: An overview of recent developments
Eliminating the negative effect of non-stationary environmental noise is a long-standing
research topic for automatic speech recognition but still remains an important challenge …
research topic for automatic speech recognition but still remains an important challenge …
An overview of noise-robust automatic speech recognition
New waves of consumer-centric applications, such as voice search and voice interaction
with mobile devices and home entertainment systems, increasingly require automatic …
with mobile devices and home entertainment systems, increasingly require automatic …
CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings
Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the
6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge …
6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge …
The fifth'CHiME'speech separation and recognition challenge: dataset, task and baselines
The CHiME challenge series aims to advance robust automatic speech recognition (ASR)
technology by promoting research at the interface of speech and language processing …
technology by promoting research at the interface of speech and language processing …
A consolidated perspective on multimicrophone speech enhancement and source separation
Speech enhancement and separation are core problems in audio signal processing, with
commercial applications in devices as diverse as mobile phones, conference call systems …
commercial applications in devices as diverse as mobile phones, conference call systems …
An analysis of environment, microphone and data simulation mismatches in robust speech recognition
Speech enhancement and automatic speech recognition (ASR) are most often evaluated in
matched (or multi-condition) settings where the acoustic conditions of the training data …
matched (or multi-condition) settings where the acoustic conditions of the training data …
Ideal ratio mask estimation using deep neural networks for robust speech recognition
A Narayanan, DL Wang - 2013 IEEE international conference …, 2013 - ieeexplore.ieee.org
We propose a feature enhancement algorithm to improve robust automatic speech
recognition (ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel …
recognition (ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel …
Multichannel audio source separation with deep neural networks
This article addresses the problem of multichannel audio source separation. We propose a
framework where deep neural networks (DNNs) are used to model the source spectra and …
framework where deep neural networks (DNNs) are used to model the source spectra and …
The first multimodal information based speech processing (misp) challenge: Data, tasks, baselines and results
In this paper we discuss the rational of the Multi-model Information based Speech
Processing (MISP) Challenge, and provide a detailed description of the data recorded, the …
Processing (MISP) Challenge, and provide a detailed description of the data recorded, the …
An unsupervised deep domain adaptation approach for robust speech recognition
S Sun, B Zhang, L Xie, Y Zhang - Neurocomputing, 2017 - Elsevier
This paper addresses the robust speech recognition problem as a domain adaptation task.
Specifically, we introduce an unsupervised deep domain adaptation (DDA) approach to …
Specifically, we introduce an unsupervised deep domain adaptation (DDA) approach to …