Publication

EXPLOITING SEQUENCE INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION

Related publications (134)

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.

Graph Regularization Network With Semantic Affinity For Weakly-Supervised Temporal Action Localization

Seungryong Kim, Jiyoung Lee

This paper presents a novel deep architecture for weakly-supervised temporal action localization that not only generates segment-level action responses but also propagates segment-level responses to the neighborhood in a form of graph Laplacian regularizat ...

IEEE2019

Shrinking Bouma's window: Visual crowding in dense displays

Michael Herzog, Gregory Francis, Adrien Christophe Doerig, Alban Bornet

In crowding, perception of a target deteriorates in the presence of nearby flankers. In the traditional feedforward framework of vision, only elements within Bouma’s window interfere with the target and adding more elements always leads to stronger crowdin ...

SAGE PUBLICATIONS LTD2019

Light Field Synthesis Using Inexpensive Surveillance Camera Systems

We present a light field synthesis technique that achieves accurate reconstruction given a low-cost, wide-baseline camera rig. Our system integrates optical flow with methods for rectification, disparity estimation, and feature extraction, which we then fe ...

2019

Estimating The Degree of Sleepiness by Integrating Articulatory Feature Knowledge In Raw Waveform Based CNNs

Julian David Fritsch, Subrahmanya Pavankumar Dubagunta

Speech-based degree of sleepiness estimation is an emerging research problem. In the literature, this problem has been mainly addressed through modeling of low level of descriptors. This paper investigates an end-to-end approach, where given raw waveform a ...

Idiap2019

Phonetic aware techniques for Speaker Verification

Subhadeep Dey

The goal of this thesis is to improve current state-of-the-art techniques in speaker verification (SV), typically based on âidentity-vectorsâ (i-vectors) and deep neural network (DNN), by exploiting diverse (phonetic) information extracted using variou ...

EPFL2018

CNN based Query by Example Spoken Term Detection

Hervé Bourlard, Dhananjay Ram

In this work, we address the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State of the art solutions usually rely on dynamic time warping (DTW) based template matching. In contrast, we propose here to tackle the pr ...

ISCA-INT SPEECH COMMUNICATION ASSOC2018

Learning embeddings: efficient algorithms and applications

Cijo Jose

Learning to embed data into a space where similar points are together and dissimilar points are far apart is a challenging machine learning problem. In this dissertation we study two learning scenarios that arise in the context of learning embeddings and o ...

EPFL2018

Learning embeddings: efficient algorithms and applications

Cijo Jose

École Polytechnique Fédérale de Lausanne2018

Evolution of Neural Network Architectures for Speech Recognition

Hervé Bourlard

Over these last few years, the use of Artificial Neural Networks (ANNs), now often referred to as deep learning or Deep Neural Networks (DNNs), has significantly reshaped research and development in a variety of signal and information processing tasks. Whi ...

ISCA-INT SPEECH COMMUNICATION ASSOC2018

Phonological Posterior Hashing for Query by Example Spoken Term Detection

Hervé Bourlard, Afsaneh Asaei, Dhananjay Ram

State of the art query by example spoken term detection (QbE-STD) systems in zero-resource conditions rely on representation of speech in terms of sequences of class-conditional posterior probabilities estimated by deep neural network (DNN). The posteriors ...

ISCA-INT SPEECH COMMUNICATION ASSOC2018