3 citations · 5 across the 11 of their papers we have counts for
7 papers · 1 filter
Listen-to-Reason: Listen with Experts, Retrieve over a Graph, Reason with LLMs
Pooneh Mousavi, Mirco Ravanelli, Cem Subakan
Large audio-language models (LALMs) fuse an audio encoder into a large language model (LLM) through multi-stage training. This coupling means that a new domain or a stronger LLM re…
AnchorPrompt: Self-Distilled Soft Prompts for Robust Audio-Language Models
Pooneh Mousavi, Amir Ivry, Mirco Ravanelli +1
Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adap…
Listen First, Then Answer: Timestamp-Grounded Speech Reasoning
Jihoon Jeong, Pooneh Mousavi, Mirco Ravanelli +1
Large audio-language models (LALMs) can generate reasoning chains for their predictions, but it remains unclear whether these reasoning chains remain grounded in the input audio. I…
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
Discrete audio tokens are compact representations that aim to preserve perceptual quality, phonetic content, and speaker characteristics while enabling efficient storage and infere…
What Are They Doing? Joint Audio-Speech Co-Reasoning
Yingzhi Wang, Pooneh Mousavi, Artem Ploujnikov +1
In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are present in the same audio clip. Recent Audito…
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?
Pooneh Mousavi, Jarod Duret, Salah Zaiem +4
Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must preserve content, paraling…
DASB - Discrete Audio and Speech Benchmark
Pooneh Mousavi, Jarod Duret, Darius Petermann +5
Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both gen…