Publication

Privacy-Sensitive Audio Features for Conversational Speech Processing

Publications associées (113)

Crowding and the importance of grouping and segmentation processes in human vision

Human vision has evolved to make sense of a world in which elements almost never appear in isolation. Surprisingly, the recognition of an element in a visual scene is strongly limited by the presence of other nearby elements, a phenomenon known as visual c ...

EPFL2021

Fair Voice Biometrics: Impact of Demographic Imbalance on Group Fairness in Speaker Recognition

Mirko Marras

Speaker recognition systems are playing a key role in modern online applications. Though the susceptibility of these systems to discrimination according to group fairness metrics has been recently studied, their assessment has been mainly focused on the di ...

ISCA-INT SPEECH COMMUNICATION ASSOC2021

Differentiable Patch Selection for Image Recognition

Jean-Baptiste Francis Marie Juliette Cordonnier, Aravindh Mahendran

Neural Networks require large amounts of memory and compute to process high resolution images, even when only a small part of the image is actually informative for the task at hand. We propose a method based on a differentiable Top-K operator to select the ...

IEEE COMPUTER SOC2021

A COMPARISON OF METHODS FOR OOV-WORD RECOGNITION ON A NEW PUBLIC DATASET

Petr Motlicek

A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose using the CommonVoi ...

IEEE Signal Processing Society2021

Multilingual Training and Adaptation in Speech Recognition

Sibo Tong

State-of-the-art acoustic models for Automatic Speech Recognition (ASR) are based on Hidden Markov Models (HMM) and Deep Neural Networks (DNN) and often require thousands of hours of transcribed speech data during training. Therefore, building multilingual ...

EPFL2020

Dynamic Model Pruning with Feedback

Martin Jaggi, Sebastian Urban Stich, Luis Felipe Barba Flores, Tao Lin, Daniil Dmitriev

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression method that gener ...

2020

COMPARISON OF SUBWORD SEGMENTATION METHODS FOR OPEN-VOCABULARYEND-TO-END SPEECH RECOGNITION

Philip Neil Garner, Claudiu-Cristian Musat

To address the open vocabulary problem in the context of end-to-end automatic speech recognition (ASR), we experiment with subword segmentation approaches, specifically byte-pair encoding and unigram language model. Such approaches are attractive in genera ...

Idiap2020

Deepfake detection: humans vs. machines

Sébastien Marcel

Deepfake videos, where a person’s face is automatically swapped with a face of someone else, are becoming easier to generate with more realistic results. In response to the threat such manipulations can pose to our trust in video evidence, several large da ...

Idiap2020

An HMM Approach with Inherent Model Selection for Sign Language and Gesture Recognition

Oya Aran, Sandrine Tornay

HMMs have been the one of the first models to be applied for sign recognition and have become the baseline models due to their success in modeling sequential and multivariate data. Despite the extensive use of HMMs for sign recognition, determining the HMM ...

ACL2020

Language Independent Query by Example Spoken Term Detection

Dhananjay Ram

Language independent query-by-example spoken term detection (QbE-STD) is the problem of retrieving audio documents from an archive, which contain a spoken query provided by a user. This is usually casted as a hypothesis testing and pattern matching problem ...

EPFL2019

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search