评测语音生成中非语言发声的准确性与自然度
NVV-SuperBench: Beyond Words, Beyond Quality-Benchmarking Nonverbal Vocalizations in Speech Generation
- 构建中英双语非语言发声评测基准，覆盖45类发声类型
- 发现语音质量与发声控制能力常不匹配，长时情感发声难处理
- 适合语音合成、人机交互研究者参考
非语言发声（NVVs），如笑声、叹息和啜泣，是实现自然语音的关键，但现有评估标准很少同时衡量系统是否生成了预期的发声、位置是否准确以及发声是否清晰。本文提出NVV-SuperBench，一个涵盖中英文的语音生成非语言发声评测基准。该基准提供统一的45类发声分类体系和多维度评估协议，超越传统语音质量评估，重点考察发声的可控性、位置准确性和感知显著性。我们对15种语音生成系统进行了评测，涵盖基于提示和基于标签的控制范式，采用客观指标、人工听感测试及大模型多评分器评估。结果表明，发声可控性常与语音质量脱钩，低信噪比口腔线索和长时间情感发声仍是主要瓶颈。NVV-SuperBench揭示了当前技术差距，助力更拟人化语音生成的发展。
原文摘要 · Abstract (English)
Nonverbal vocalizations (NVVs), such as laughing, sighing, and sobbing, are essential for human-like speech, yet standardized evaluation rarely jointly assesses whether systems generate the intended NVVs, place them correctly, and keep them salient without harming speech. We present NVV-SuperBench, a bilingual English/Chinese benchmark for speech generation with NVVs. It provides a unified 45-type taxonomy and a multi-axis protocol beyond conventional speech quality assessment, evaluating NVV-specific controllability, placement, and perceptual salience. We benchmark 15 speech generation systems spanning prompt-based and tag-based control paradigms, using objective metrics, human listening tests, and LLM-based multi-rater evaluation. Results show that NVV controllability often decouples from speech quality, while low-SNR oral cues and long-duration affective NVVs remain bottlenecks. NVV-SuperBench highlights current gaps and supports progress toward more human-like speech generation.
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。