Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.06829 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917194908041216 |
|---|---|
| author | Sun, Bochao Xiao, Yang Yin, Han |
| author_facet | Sun, Bochao Xiao, Yang Yin, Han |
| contents | Recent advances in generative models have enabled modern Text-to-Audio (TTA) systems to synthesize audio with high perceptual quality. However, TTA systems often struggle to maintain semantic consistency with the input text, leading to mismatches in sound events, temporal tructures, or contextual relationships. Evaluating semantic fidelity in TTA remains a significant challenge. Traditional methods primarily rely on subjective human listening tests, which is time-consuming. To solve this, we propose an objective evaluator based on a Mixture of Experts (MoE) architecture with Sequential Cross-Attention (SeqCoAttn). Our model achieves the first rank in the XACLE Challenge, with an SRCC of 0.6402 (an improvement of 30.6% over the challenge baseline) on the test dataset. Code is available at: https://github.com/S-Orion/MOESCORE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06829 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System Evaluation Sun, Bochao Xiao, Yang Yin, Han Sound Recent advances in generative models have enabled modern Text-to-Audio (TTA) systems to synthesize audio with high perceptual quality. However, TTA systems often struggle to maintain semantic consistency with the input text, leading to mismatches in sound events, temporal tructures, or contextual relationships. Evaluating semantic fidelity in TTA remains a significant challenge. Traditional methods primarily rely on subjective human listening tests, which is time-consuming. To solve this, we propose an objective evaluator based on a Mixture of Experts (MoE) architecture with Sequential Cross-Attention (SeqCoAttn). Our model achieves the first rank in the XACLE Challenge, with an SRCC of 0.6402 (an improvement of 30.6% over the challenge baseline) on the test dataset. Code is available at: https://github.com/S-Orion/MOESCORE. |
| title | MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System Evaluation |
| topic | Sound |
| url | https://arxiv.org/abs/2601.06829 |