arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03310eess.AScs.LGcs.SD
收藏

MTI-Net:一种多目标语音清晰度预测模型

MTI-Net: A Multi-Target Speech Intelligibility Prediction Model

National Taiwan University(国立台湾大学);Academia Sinica(中央研究院);Microsoft Corporation(微软公司);Southern University of Science and Technology of China(南方科技大学)

Ryandhimas E. Zezario, Szu-wei Fu, Fei Chen, Chiou-Shann Fuh, Hsin-Min Wang, Yu Tsao

摘要:

近年来,基于深度学习(DL)的非侵入式语音评估模型引起了人们的极大关注。许多研究报告说,这些基于DL的模型产生令人满意的评估性能和良好的灵活性,但他们在看不见的环境中的性能仍然是一个挑战。此外,与质量分数相比,很少有研究详细阐述深度学习模型来估计可懂度分数。本研究提出了一个多任务语音清晰度预测模型,称为MTI-Net,同时预测人类和机器的清晰度措施。具体而言,给定一个语音话语,MTI-Net被设计用于预测人类主观听力测试结果和单词错误率(WER)分数。我们还研究了几种可以提高MTI-Net预测性能的方法。首先,我们比较了MTI-Net的不同特征(包括低级特征和自监督学习(SSL)模型的嵌入)和预测目标。其次,我们探讨了迁移学习和多任务学习对训练MTI-Net的影响。最后,我们研究了微调SSL嵌入的潜在优势。实验结果证明了使用跨域特征、多任务学习和微调SSL嵌入的有效性。此外,它被证实,MTI-Net预测的可懂度和WER分数与地面实况分数高度相关。

英文摘要:

Recently, deep learning (DL)-based non-intrusive speech assessment models have attracted great attention. Many studies report that these DL-based models yield satisfactory assessment performance and good flexibility, but their performance in unseen environments remains a challenge. Furthermore, compared to quality scores, fewer studies elaborate deep learning models to estimate intelligibility scores. This study proposes a multi-task speech intelligibility prediction model, called MTI-Net, for simultaneously predicting human and machine intelligibility measures. Specifically, given a speech utterance, MTI-Net is designed to predict human subjective listening test results and word error rate (WER) scores. We also investigate several methods that can improve the prediction performance of MTI-Net. First, we compare different features (including low-level features and embeddings from self-supervised learning (SSL) models) and prediction targets of MTI-Net. Second, we explore the effect of transfer learning and multi-tasking learning on training MTI-Net. Finally, we examine the potential advantages of fine-tuning SSL embeddings. Experimental results demonstrate the effectiveness of using cross-domain features, multi-task learning, and fine-tuning SSL embeddings. Furthermore, it is confirmed that the intelligibility and WER scores predicted by MTI-Net are highly correlated with the ground-truth scores.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑