HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908425415294976 |
|---|---|
| author | Ren, Wenze Lin, Yi-Cheng Huang, Wen-Chin Zezario, Ryandhimas E. Fu, Szu-Wei Huang, Sung-Feng Cooper, Erica Wu, Haibin Wei, Hung-Yu Wang, Hsin-Min Lee, Hung-yi Tsao, Yu |
| author_facet | Ren, Wenze Lin, Yi-Cheng Huang, Wen-Chin Zezario, Ryandhimas E. Fu, Szu-Wei Huang, Sung-Feng Cooper, Erica Wu, Haibin Wei, Hung-Yu Wang, Hsin-Min Lee, Hung-yi Tsao, Yu |
| contents | Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first non-intrusive mean opinion score (MOS) model that explicitly considers sampling rate. HighRateMOS ensembles three model variants that exploit the following information: (i) a learnable embedding of speech sampling rate, (ii) Wav2vec 2.0 self-supervised embeddings, (iii) multi-scale CNN spectral features, and (iv) MFCC features. In AudioMOS 2025 Track3, HighRateMOS ranked first in five out of eight metrics. Our experiments confirm that modeling the sampling rate directly leads to more robust and sampling-rate-agnostic speech quality predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_21951 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment Ren, Wenze Lin, Yi-Cheng Huang, Wen-Chin Zezario, Ryandhimas E. Fu, Szu-Wei Huang, Sung-Feng Cooper, Erica Wu, Haibin Wei, Hung-Yu Wang, Hsin-Min Lee, Hung-yi Tsao, Yu Audio and Speech Processing Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first non-intrusive mean opinion score (MOS) model that explicitly considers sampling rate. HighRateMOS ensembles three model variants that exploit the following information: (i) a learnable embedding of speech sampling rate, (ii) Wav2vec 2.0 self-supervised embeddings, (iii) multi-scale CNN spectral features, and (iv) MFCC features. In AudioMOS 2025 Track3, HighRateMOS ranked first in five out of eight metrics. Our experiments confirm that modeling the sampling rate directly leads to more robust and sampling-rate-agnostic speech quality predictions. |
| title | HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.21951 |