activity
20232025
most citedPosthoc Interpretation via Quantization

4 citations · 5 across the 6 of their papers we have counts for

collaborators

6 papers

eess.AS2025

Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease

Peter Plantinga, Roozbeh Sattari, Karine Marcotte +8

The speech of people with Parkinson's Disease (PD) has been shown to hold important clues about the presence and progression of the disease. We investigate the factors based on whi…

cs.AI2025

LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs

Pooneh Mousavi, Shubham Gupta, Cem Subakan +1

Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting these models for general-purpose audio-…

cs.SD2024

Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech

Eleonora Mancini, Francesco Paissan, Paolo Torroni +2

Speech impairments in Parkinson's disease (PD) provide significant early indicators for diagnosis. While models for speech-based PD detection have shown strong performance, their i…

eess.AS20231 cited

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

Jeff Hwang, Moto Hira, Caroline Chen +21

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims to accelerate the research and development of audio and speech technologies by providing…

cs.LG2023

Simulated Annealing in Early Layers Leads to Better Generalization

Amirmohammad Sarfi, Zahra Karimpour, Muawiz Chaudhary +4

Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer periods of time in exchange for improve…

cs.AI20234 cited

Posthoc Interpretation via Quantization

Francesco Paissan, Cem Subakan, Mirco Ravanelli

In this paper, we introduce a new approach, called Posthoc Interpretation via Quantization (PIQ), for interpreting decisions made by trained classifiers. Our method utilizes vector…