# DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction

arXiv: https://arxiv.org/abs/2508.21407 · HTML: https://mlsanity.com/paper/2508.21407/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Fr'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms](https://mlsanity.com/paper/1812.08466/) (2018)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [Attentive Statistics Pooling for Deep Speaker Embedding](https://mlsanity.com/paper/1803.10963/) (2018)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization](https://mlsanity.com/paper/2404.09956/) (2024)
- [MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies](https://mlsanity.com/paper/2308.01546/) (2023)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [Masked Audio Generation using a Single Non-Autoregressive Transformer](https://mlsanity.com/paper/2401.04577/) (2024)
- [Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System](https://mlsanity.com/paper/1804.05160/) (2018)
- [Neural Aggregation Network for Video Face Recognition](https://mlsanity.com/paper/1603.05474/) (2016)
- [Quality Aware Network for Set to Set Recognition](https://mlsanity.com/paper/1704.03373/) (2017)
- [MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation](https://mlsanity.com/paper/2501.10811/) (2025)
- [GhostVLAD for set-based face recognition](https://mlsanity.com/paper/1810.09951/) (2018)
- [Self Multi-Head Attention for Speaker Recognition](https://mlsanity.com/paper/1906.09890/) (2019)
- [VoiceID Loss: Speech Enhancement for Speaker Verification](https://mlsanity.com/paper/1904.03601/) (2019)
- [RSKNet-MTSP: Effective and Portable Deep Architecture for Speaker Verification](https://mlsanity.com/paper/2108.13249/) (2021)
- [Deep Segment Attentive Embedding for Duration Robust Speaker Verification](https://mlsanity.com/paper/1811.00883/) (2018)

## Built on by (most cited first, 2 of 2)

- [Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations](https://mlsanity.com/paper/2603.16201/) (2026)
- [DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment](https://mlsanity.com/paper/2606.10010/) (2026)

## Abstract (arXiv)

A pooling mechanism is essential for mean opinion score (MOS) prediction, facilitating the transformation of variable-length audio features into a concise fixed-size representation that effectively encodes speech quality. Existing pooling methods typically operate at a singular granularity, concentrating either on a comprehensive global perspective or a detailed frame-level analysis, which may overlook complementary perceptual insights. To address this limitation, we introduce the Dual-Resolution Attentive Statistics Pooling (DRASP) framework. DRASP integrates both coarse-grained, global statistical summaries and fine-grained, attentive analyses of perceptually significant segments. This dual-view architecture empowers our model to formulate a more thorough and robust representation, capturing both the overarching structural context and salient local details concurrently. Extensive experiments validate the effectiveness and strong generalization ability of the proposed framework. It consistently outperforms various baseline methods across diverse datasets (MusicEval and AES-Natural), MOS prediction backbones (including a CLAP-based model and AudioBox-Aesthetics), and different audio generation systems, achieving a relative improvement of 10.39% in system-level Spearman's rank correlation coefficient (SRCC) over the widely-used average pooling approach.