activity
20242026
collaborators

5 papers

cs.SD2026

Performance and Complexity Trade-off Optimization of Speech Models During Training

Esteban Gómez, Tom Backström

In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. These models are then trained to maximize…

cs.LG2026

DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick

Mohammad Hassan Vali, Tom Bäckström, Arno Solin

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an erro…

eess.AS2025

Privacy Disclosure of Similarity Rank in Speech and Language Processing

Tom Bäckström, Mohammad Hassan Vali, My Nguyen +1

Speaker, author, and other biometric identification applications often compare a sample's similarity to a database of templates to determine the identity. Given that data may be no…

cs.CV2025

Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

Mohammad Hassan Vali, Tom Bäckström

Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised…

cs.LG2024

Good practices for evaluation of machine learning systems

Luciana Ferrer, Odette Scharenborg, Tom Bäckström

Many development decisions affect the results obtained from ML experiments: training data, features, model architecture, hyperparameters, test data, etc. Among these aspects, argua…