Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Coldenhoff, Jozef, Cernak, Milos
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913659708506112
author Coldenhoff, Jozef
Cernak, Milos
author_facet Coldenhoff, Jozef
Cernak, Milos
contents Human perception has the unique ability to focus on specific events in a mixture of signals--a challenging task for existing non-intrusive assessment methods. In this work, we introduce semi-intrusive assessment that emulates human attention by framing audio assessment as a text-prediction task with audio-text inputs. To this end, we extend the multi-modal PENGI model through instruction fine-tuning for MOS and SNR estimation. For MOS, our approach achieves absolute Pearson correlation gains of 0.06 and 0.20 over the re-trained MOSRA model and the pre-trained PAM model, respectively. We further propose a novel SNR estimator that can focus on a specific audio source in a mixture, outperforming a random baseline and the fixed-prompt counterpart. Our findings suggest that semi-intrusive assessment can effectively capture human-like selective listening capabilities. Samples are available at https://jozefcoldenhoff.github.io/semi-intrusive-assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task
Coldenhoff, Jozef
Cernak, Milos
Audio and Speech Processing
Sound
Human perception has the unique ability to focus on specific events in a mixture of signals--a challenging task for existing non-intrusive assessment methods. In this work, we introduce semi-intrusive assessment that emulates human attention by framing audio assessment as a text-prediction task with audio-text inputs. To this end, we extend the multi-modal PENGI model through instruction fine-tuning for MOS and SNR estimation. For MOS, our approach achieves absolute Pearson correlation gains of 0.06 and 0.20 over the re-trained MOSRA model and the pre-trained PAM model, respectively. We further propose a novel SNR estimator that can focus on a specific audio source in a mixture, outperforming a random baseline and the fixed-prompt counterpart. Our findings suggest that semi-intrusive assessment can effectively capture human-like selective listening capabilities. Samples are available at https://jozefcoldenhoff.github.io/semi-intrusive-assessment.
title Semi-intrusive audio evaluation: Casting non-intrusive assessment as a multi-modal text prediction task
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2409.14069