CodecMOS-Accent：神经编码器与TTS语音跨英语口音的MOS基准
CodecMOS-Accent: A MOS Benchmark of Resynthesized and TTS Speech from Neural Codecs Across English Accents
AI总结：
本文提出CodecMOS-Accent数据集，用于评估神经音频编码器和基于LLM的TTS模型，尤其针对非标准语音如口音。数据集包含24系统生成的4000个样本，涵盖10种口音，通过大规模主观测试收集19600条注解，揭示了说话人与口音相似性之间的紧密关系及客观指标的预测能力。
摘要：
我们提出了CodecMOS-Accent数据集，一个用于评估神经音频编码器（NAC）模型和基于大语言模型（LLM）的文本到语音（TTS）模型的MOS基准，特别针对非标准语音如口音。该数据集包含来自24个系统的4000个编码重合成和TTS样本，涵盖10种口音的32名说话人。通过大规模主观测试，收集了25名听众在自然度、说话人相似性和口音相似性三个维度上的19600条注解。该数据集不仅代表了近期语音合成系统性能的最新研究，还揭示了说话人与口音相似性之间的紧密关系、客观指标的预测能力以及当听众与说话人具有相同口音时的感知偏差。该数据集预计将促进更以人为中心的NAC和口音TTS评估研究。
英文摘要：
We present the CodecMOS-Accent dataset, a mean opinion score (MOS) benchmark designed to evaluate neural audio codec (NAC) models and the large language model (LLM)-based text-to-speech (TTS) models trained upon them, especially across non-standard speech like accented speech. The dataset comprises 4,000 codec resynthesis and TTS samples from 24 systems, featuring 32 speakers spanning ten accents. A large-scale subjective test was conducted to collect 19,600 annotations from 25 listeners across three dimensions: naturalness, speaker similarity, and accent similarity. This dataset does not only represent an up-to-date study of recent speech synthesis system performance but reveals insights including a tight relationship between speaker and accent similarity, the predictive power of objective metrics, and a perceptual bias when listeners share the same accent with the speaker. This dataset is expected to foster research on more human-centric evaluation for NAC and accented TTS.
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。
