Search Results for author:
Found 20 papers, 11 papers with code
Weakly supervised discourse segmentation for multiparty oral conversations
Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks.
Audio classification with Dilated Convolution with Learnable Spacings
Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation.
Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval?
For ATR, we propose using the standard Cross-Entropy loss values obtained for any audio/caption pair.
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable.
Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates
For this reason, several complementary metrics, such as BLEU, CIDEr, SPICE and SPIDEr, are used to compare a single automatic caption to one or several captions of reference, produced by a human annotator.
Audio-video fusion strategies for active speaker detection in meetings
In this paper, we propose two different types of fusion for the detection of the active speaker, combining two visual modalities and an audio modality through neural networks.
Dilated convolution with learnable spacings
We call this method "Dilated Convolution with Learnable Spacings" (DCLS) and generalize it to the n-dimensional convolution case.
End-to-end acoustic modelling for phone recognition of young readers
Through transfer learning, a Transformer model complemented with a Connectionist Temporal Classification (CTC) objective function, reaches a phone error rate of 28. 1%, outperforming a state-of-the-art DNN-HMM model by 6. 6% relative, as well as other end-to-end architectures by more than 8. 5% relative.
Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning
Multi-label audio tagging consists of assigning sets of tags to audio recordings.
Comparison of semi-supervised deep learning algorithms for audio classification
In all but one cases, MM, RMM, and FM outperformed MT and DCT significantly, MM and RMM being the best methods in most experiments.
Low-activity supervised convolutional spiking neural networks applied to speech commands recognition
Deep Neural Networks (DNNs) are the current state-of-the-art models in many speech related tasks.
Informations segmentales pour la caract\'erisation phon\'etique du locuteur : variabilit\'e inter- et intra-locuteurs (An automatic classification task involving 44 speakers was performed using convolutional neural networks (CNN) on broadband spectrograms extracted from 2-second sequences of a spontaneous speech corpus (NCCFr))
Les r{\'e}sultats montrent que les voyelles orales influent avant toute autre classe sur le taux de classification, suivies ensuite par les occlusives orales.
Reconnaissance de phones fond\'ee sur du Transfer Learning pour des enfants apprenants lecteurs en environnement de classe (Transfer Learning based phone recognition on children learning to read, with speech recorded in a classroom environment)
A conditions {\'e}gales, les performances actuelles de la reconnaissance vocale pour enfants sont inf{\'e}rieures {\`a} celles des syst{\`e}mes pour adultes.
Technical report: supervised training of convolutional spiking neural networks with PyTorch
Indeed, the most commonly used spiking neuron model, the leaky integrate-and-fire neuron, obeys a differential equation which can be approximated using discrete time steps, leading to a recurrent relation for the potential.
Evaluation of post-processing algorithms for polyphonic sound event detection
We compared post-processing algorithms on the temporal prediction curves of two models: one based on the challenge's baseline and a Multiple Instance Learning (MIL) model.
Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection
In this work, we address Sound Event Detection in the case where a weakly annotated dataset is available for training.
Sound Audio and Speech Processing
R\'eseau de neurones convolutif pour l'\'evaluation automatique de la prononciation (CNN-based automatic pronunciation assessment of Japanese speakers learning French )
Un gain de performance relatif de 13, 4{\%} a {\'e}t{\'e} obtenu avec le CNN, avec une pr{\'e}cision globale de 72, 6{\%}, sur un corpus d{'}{\'e}valuation enregistr{\'e} par 23 locuteurs japonophones.
Influence de la quantit\'e de donn\'ees sur une t\^ache de segmentation de phones fond\'ee sur les r\'eseaux de neurones (Phone-level speech segmentation with neural networks : influence of the amount of data )
Dans cet article, nous d{\'e}crivons une {\'e}tude exp{\'e}rimentale de segmentation de parole en unit{\'e}s acoustiques sous-lexicales (phones) {\`a} l{'}aide de r{\'e}seaux de neurones.
El-WOZ: a client-server wizard-of-oz interface
In order to collect spontaneous speech in a situation of interaction with a machine, this interface was designed as a Wizard-of-Oz (WOZ) plateform.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
