Nonlinear feature transformations for noise robust speech recognition
Related publications (91)
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The thesis work was motivated by the goal of developing personalized speech-to-speech translation and focused on one of its key component techniques – cross-lingual speaker adaptation for text-to-speech synthesis. A personalized speech-to-speech translator ...
Coherency group identification is an integral constituent part of the wider field of reduction techniques in power systems. It consists of separating the machines in the system into groups that feature similar behavior. This paper presents a coherency iden ...
In this paper, we present a new algorithm to estimate a signal from its short-time Fourier transform modulus (STFTM). This algorithm is computationally simple and is obtained by an acceleration of the well-known Griffin-Lim algorithm (GLA). Before deriving ...
In this paper, a low complexity system for spectral analysis of heart rate variability (HRV) is presented. The main idea of the proposed approach is the implementation of the Fast-Lomb periodogram that is a ubiquitous tool in spectral analysis, using a wav ...
In this paper, we introduce a new class of noise robust features derived from an alternative measure of autocorrelation representing the phase variation of speech signal frame over time. These features, referred to as Phase AutoCorrelation (PAC) features i ...
We present a novel plenoptic sampling scheme that permits an efficient representation of the full light ray field in a space limited by a convex closed surface. We show that a convenient way to sample the light ray field around an observer consists in usin ...
In this thesis, the problem of the transverse coupled-bunch instabilities created by the Large Hadron Collider (LHC) beam-coupling impedance, that can possibly limit the machine operation, is addressed thanks to several new theories and tools. A rather com ...
One of the main challenge in non-native speech recognition is how to handle acoustic variability present in multiaccented non-native speech with limited amount of training data. In this paper, we investigate an approach that addresses this challenge by usi ...
A procedure for time-frequency analysis of time series is described, which is mainly inspired by singular-spectrum analysis, but it presents some modifications that allow checking the convergence of the results and extracting the detected spectral componen ...
In this paper, we propose a novel parts-based binary-valued feature for ASR. This feature is extracted using boosted ensembles of simple threshold-based classifiers. Each such classifier looks at a specific pair of time-frequency bins located on the spectr ...