26 papers
Controllable and Content-Based Recommendations
Fırat Ãncel, Jihoon Jeong, Emiliano Penaloza +3
Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpret and control. We propose the Controllable and Content-Based Recommendat…
Self-Routing: Parameter-Free Expert Routing from Hidden States
Jama Hussein Mohamud, Drew Wagner, Mirco Ravanelli
Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned router to map hidden states to exper…
HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models
Artem Ploujnikov, Francesco Verdini, Samir Sadok +1
Discrete audio representations have become increasingly popular for building multimodal text-audio systems and integrating audio capabilities into Large Language Models (LLMs). How…
Investigating Faithfulness in Large Audio Language Models
Pooneh Mousavi, Lovenya Jain, Mirco Ravanelli +1
Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks. While these models can generate Ch…
ALAS: An Automatic Latent Alignment Score for Audio Language Models
Pooneh Mousavi, Yingzhi Wang, Mirco Ravanelli +1
Large Language Models (LLMs) are extended into Speech-LLMs, and the quality of the audio--text alignment they learn affects most downstream Spoken Language Understanding (SLU) beha…
MambAdapter: Lightweight Mamba-Based Adapters for Parameter-Efficient Transfer Learning in Speech and Audio
Salman Hussain Ali, Umberto Cappellazzo, Mirco Ravanelli
Fine-tuning Transformer-based foundation models has become the dominant strategy for domain adaptation in audio and speech processing. To reduce the computational and memory costs…