RF-GML: Reference-Free Generative Machine Listener
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916537121636352 |
|---|---|
| author | Biswas, Arijit Jiang, Guanxin |
| author_facet | Biswas, Arijit Jiang, Guanxin |
| contents | This paper introduces a novel reference-free (RF) audio quality metric called the RF-Generative Machine Listener (RF-GML), designed to evaluate coded mono, stereo, and binaural audio at a 48 kHz sample rate. RF-GML leverages transfer learning from a state-of-the-art full-reference (FR) Generative Machine Listener (GML) with minimal architectural modifications. The term "generative" refers to the model's ability to generate an arbitrary number of simulated listening scores. Unlike existing RF models, RF-GML accurately predicts subjective quality scores across diverse content types and codecs. Extensive evaluations demonstrate its superiority in rating unencoded audio and distinguishing different levels of coding artifacts. RF-GML's performance and versatility make it a valuable tool for coded audio quality assessment and monitoring in various applications, all without the need for a reference signal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10210 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RF-GML: Reference-Free Generative Machine Listener Biswas, Arijit Jiang, Guanxin Audio and Speech Processing Sound This paper introduces a novel reference-free (RF) audio quality metric called the RF-Generative Machine Listener (RF-GML), designed to evaluate coded mono, stereo, and binaural audio at a 48 kHz sample rate. RF-GML leverages transfer learning from a state-of-the-art full-reference (FR) Generative Machine Listener (GML) with minimal architectural modifications. The term "generative" refers to the model's ability to generate an arbitrary number of simulated listening scores. Unlike existing RF models, RF-GML accurately predicts subjective quality scores across diverse content types and codecs. Extensive evaluations demonstrate its superiority in rating unencoded audio and distinguishing different levels of coding artifacts. RF-GML's performance and versatility make it a valuable tool for coded audio quality assessment and monitoring in various applications, all without the need for a reference signal. |
| title | RF-GML: Reference-Free Generative Machine Listener |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2409.10210 |