Neural music editing requires a system to perform a requested change while preserving the musical content that should remain unchanged. Existing evaluations often lack a paired target edit, making these requirements difficult to measure separately. We introduce SMEBench, a large-scale benchmark of controlled music edit...
Matthieu Cervera, F. Paissan, Micael Antunes et al.· 0 citations
SpecAugment is the dominant speech augmentation policy, but researchers have studied it primarily for automatic speech recognition (ASR), and it operates on spectrograms, limiting its applicability to other speech tasks and waveform models. We propose Wav2Aug, a drop-in waveform augmentation policy that randomly sample...
Gianfranco Dumoulin Bertucci, M. Ravanelli· 0 citations
Listen-to-Reason (L2R), an interpretable-by-design pipeline that passes audio to the LLM through an explicit, human-readable tree that outperforms all LALMs the authors compare against on SAKURA and trails them by 6-12 points on MMAU and MMAR, is proposed.
Pooneh Mousavi, M. Ravanelli, Cem Subakan· 0 citations
Large audio-language models (LALMs) are sensitive to input perturbations, such as noise, waveform corruption, and adversarial injections. We propose AnchorPrompt, an efficient adaptation method that keeps the model frozen and learns a single block of prompt vectors inserted at the decoder input, between the audio and q...
Pooneh Mousavi, Amir Ivry, M. Ravanelli et al.· 0 citations
Recursive models create computational depth through parameter reuse, offering a parameter-efficient alternative to increasing model size. However, most recursive models repeatedly apply one learned transformation or a prescribed sequence of transformations, restricting computation to a fixed layer order. We introduce t...
GLaS-JEPA is presented, a framework that directly predicts the current encoder's continuous representations at masked positions, without contrastive learning, discrete targets, or separate EMA target encoders, and prevents representation collapse using SIGReg representation-space regularization.
G. Botté, Séverin Baroudi, Samir Sadok et al.· arXiv.org· 0 citations
Applying ALAS to four open-source Speech-LLMs across emotion recognition, open-ended SQA, and multi-choice audio understanding, it is found that the depth and strength of alignment reflect each model's audio-encoder design and the acoustic-versus-semantic demands of the task, and that ALAS tracks but does not duplicate...
Pooneh Mousavi, Yingzhi Wang, M. Ravanelli et al.· 4 citations
This work evaluates continued pretraining on FineWeb-Edu dumps drawn strictly from after each model's knowledge cutoff, evaluated across six open-weight models spanning three families and four parameter scales, painting a more optimistic picture of time-incremental CPT than the prior continual learning literature sugge...
Firat Öncel, S. Ali, M. Ravanelli et al.· arXiv.org· 0 citations
SPARE (Semantic Prediction for Audio REasoning), which introduces a register token aligned with the final conclusion using a cosine similarity loss with a Sentence-BERT embedding, conditions the model's latent space with the target semantic goal before reasoning begins.
Francesco Bonzi, Pooneh Mousavi, Cem Subakan et al.· 2 citations
Experiments show that ZipCodec substantially outperforms existing streaming codecs at comparable bitrates in both reconstruction and downstream tasks, while operating at a significantly lower frame rate.
Luca Della Libera, Cem Subakan, M. Ravanelli· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.