21 citations · 22 across the 10 of their papers we have counts for
12 papers
Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers
Yacouba Kaloga, Shashi Kumar, Shakeel A. Sheikh +3
End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for improved recognition without trai…
Geometric Latent Reasoning Induces Shorter Generations in LLMs
Shashi Kumar, Yacouba Kaloga, Petr Motlicek +2
Large language models solve complex problems by generating lengthy chains of explicit reasoning tokens. While effective, this makes reasoning expensive, length-sensitive, and const…
CLAP-Based Automatic Word Naming Recognition in Post-Stroke Aphasia
Yacouba Kaloga, Marina Laganaro, Ina Kodrasi
Conventional automatic word-naming recognition systems struggle to recognize words from post-stroke patients with aphasia because of disfluencies and mispronunciations, limiting re…
Latent Space Factorization in LoRA
Shashi Kumar, Yacouba Kaloga, John Mitros +2
Low-rank adaptation (LoRA) is a widely used method for parameter-efficient finetuning. However, existing LoRA variants lack mechanisms to explicitly disambiguate task-relevant info…
Towards interpretable emotion recognition: Identifying key features with machine learning
Yacouba Kaloga, Ina Kodrasi
Unsupervised methods, such as wav2vec2 and HuBERT, have achieved state-of-the-art performance in audio tasks, leading to a shift away from research on interpretable features. Howev…
A Differentiable Alignment Framework for Sequence-to-Sequence Modeling via Optimal Transport
Yacouba Kaloga, Shashi Kumar, Petr Motlicek +1
Accurate sequence-to-sequence (seq2seq) alignment is critical for applications like medical speech analysis and language learning tools relying on automatic speech recognition (ASR…
Graph Neural Networks for Parkinsons Disease Detection
Shakeel A. Sheikh, Yacouba Kaloga, Md Sahidullah +1
Despite the promising performance of state of the art approaches for Parkinsons Disease (PD) detection, these approaches often analyze individual speech segments in isolation, whic…
Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection
Yacouba Kaloga, Shakeel A. Sheikh, Ina Kodrasi
Recently proposed automatic pathological speech detection approaches rely on spectrogram input representations or wav2vec2 embeddings. These representations may contain pathology i…
A Simple Way to Learn Metrics Between Attributed Graphs
Yacouba Kaloga, Pierre Borgnat, Amaury Habrard
The choice of good distances and similarity measures between objects is important for many machine learning methods. Therefore, many metric learning algorithms have been developed…
Multiview Variational Graph Autoencoders for Canonical Correlation Analysis
Yacouba Kaloga, Pierre Borgnat, Sundeep Prabhakar Chepuri +2
We present a novel multiview canonical correlation analysis model based on a variational approach. This is the first nonlinear model that takes into account the available graph-bas…
Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
Louis Béthune, Yacouba Kaloga, Pierre Borgnat +2
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literatu…
Criterion for fingering instabilities in colloidal gels
Thibaut Divoux, Asheesh Shukla, Badis Marsit +2
We sandwich a colloidal gel between two parallel plates and induce a radial flow by lifting the upper plate at a constant velocity. Two distinct scenarios result from such a tensil…