Publication
Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition
Publications associées (42)
A t-distribution based operator for enhancing out of distribution robustness of neural network classifiers
Neural Network (NN) classifiers can assign extreme probabilities to samples that have not appeared during training (out-of-distribution samples) resulting in erroneous and unreliable predictions. One of the causes for this unwanted behaviour lies in the us ...
IEEE2020On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks.
Deep neural networks have been empirically successful in a variety of tasks, however their theoretical understanding is still poor. In particular, modern deep neural networks have many more parameters than training data. Thus, in principle they should over ...
EPFL2020Language Independent Query by Example Spoken Term Detection
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 ...
EPFL2019Biologically plausible deep learning – but how far can we go with shallow networks?
Wulfram Gerstner, Johanni Michael Brea, Bernd Albert Illing
Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining s ...
2019Template-matching for text-dependent speaker verification
In the last decade, i-vector and Joint Factor Analysis (JFA) approaches to speaker modeling have become ubiquitous in the area of automatic speaker recognition. Both of these techniques involve the computation of posterior probabilities, using either Gauss ...
2017Low-Rank Representation For Enhanced Deep Neural Network Acoustic Models
Automatic speech recognition (ASR) is a fascinating area of research towards realizing humanmachine interactions. After more than 30 years of exploitation of Gaussian Mixture Models (GMMs), state-of-the-art systems currently rely on Deep Neural Network (DN ...
Idiap2016Efficient Posterior Exemplar Search Space Hashing Exploiting Class-Specific Sparsity Structures
Hervé Bourlard, Milos Cernak, Afsaneh Asaei
This paper shows that exemplar-based speech processing using class-conditional posterior probabilities admits a highly effective search strategy relying on posteriors' intrinsic sparsity structures. The posterior probabilities are estimated for phonetic an ...
2016Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures
Hervé Bourlard, Milos Cernak, Afsaneh Asaei
This paper shows that exemplar-based speech processing using class-conditional posterior probabilities admits a highly effective search strategy relying on posteriors' intrinsic sparsity structures. The posterior probabilities are estimated for phonetic an ...
Idiap2016Towards End-to-End Speech Recognition
Standard automatic speech recognition (ASR) systems follow a divide and conquer approach to convert speech into text. Alternately, the end goal is achieved by a combination of sub-tasks, namely, feature extraction, acoustic modeling and sequence decoding, ...
EPFL2016Sound Pattern Matching for Automatic Prosodic Event Detection
Hervé Bourlard, Philip Neil Garner, Milos Cernak, Afsaneh Asaei, Pierre-Edouard Jean Charles Honnet
Prosody in speech is manifested by variations of loudness, exaggeration of pitch, and specific phonetic variations of prosodic segments. For example, in the stressed and unstressed syllables, there are differences in place or manner of articulation, vowels ...
Idiap2016