通过跨域特征重要性分析，提升助听器语音可懂度预测精度
Feature Importance across Domains for Improving Non-Intrusive Speech Intelligibility Prediction in Hearing Aids
- 基于时频域与Whisper隐表示的特征重要性加权，动态聚焦关键信息
- 在MBI-Net+模型中引入后，均方根误差降低7.62%至24.11
- 适用于需高精度语音可懂度评估的助听器系统研发
鉴于非侵入式语音可懂度评估在助听器中的关键作用，本文提出跨域特征重要性（FiDo）方法，对频谱、时域声学特征及Whisper的潜在表示进行特征重要性估计。重要性权重按帧计算，将特征投影至新空间，使模型早期聚焦关键区域。随后进行特征拼接，再由评估模块处理。实验表明，将FiDo融入改进的多分支语音可懂度模型MBI-Net+后，均方根误差从26.10降至24.11，降低7.62%；相较于2023年清晰度预测挑战赛最优系统，相对误差减少3.98%。结果验证了FiDo在提升助听器神经语音评估性能方面的有效性。
原文摘要 · Abstract (English)
Given the critical role of non-intrusive speech intelligibility assessment in hearing aids (HA), this paper enhances its performance by introducing Feature Importance across Domains (FiDo). We estimate feature importance on spectral and time-domain acoustic features as well as latent representations of Whisper. Importance weights are calculated per frame, and based on these weights, features are projected into new spaces, allowing the model to focus on important areas early. Next, feature concatenation is performed to combine the features before the assessment module processes them. Experimental results show that when FiDo is incorporated into the improved multi-branched speech intelligibility model MBI-Net+, RMSE can be reduced by 7.62% (from 26.10 to 24.11). MBI-Net+ with FiDo also achieves a relative RMSE reduction of 3.98% compared to the best system in the 2023 Clarity Prediction Challenge. These results validate FiDo's effectiveness in enhancing neural speech assessment in HA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。