← 研踪 PaperTrailarXiv:2611.20822 · v1
No-Shot Text-to-Speech: Limitations of Zero-Shot TTS and its Evaluation Methods in Representing Queer and Transgender Voices
首次提交 2026-11-16 18:05
版本更新 2026-11-16 18:05
雷达观测 2026-11-17 17:11
摘要
Gender expansive voices remain underrepresented in speech datasets, which could cause challenges with generalizability in zero-shot Text-To-Speech (TTS) systems. We evaluate six zero-shot TTS models on two datasets: one containing non gender expansive voices (N-GE) and one with gender expansive (GE) voices from self-identified speakers. Human ratings found that 2 of the 6 models synthesize less similar GE voices compared to N-GE voices, and 3 have improved performance for GE voices. Automated evaluations yield conflicting results, with speaker similarity and automated mean opinion score predictors rating performance of GE voices inconsistently between models and human ratings. This highlights a potential blind spot in evaluation pipelines, emphasizing a need for more representative data and metrics that better capture human perceptual judgments. Our findings stress the need to include transgender, queer, and minority communities in creation of better datasets and model training.
作者备注:Proceedings of Interspeech 2026
期刊信息:Proc. Interspeech 2026, 3674-3679
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 18:05 · 最新观测版本
No-Shot Text-to-Speech: Limitations of Zero-Shot TTS and its Evaluation Methods in Representing Queer and Transgender Voices
Gender expansive voices remain underrepresented in speech datasets, which could cause challenges with generalizability in zero-shot Text-To-Speech (TTS) systems. We evaluate six zero-shot TTS models on two datasets: one containing non gender expansive voices (N-GE) and one with gender expansive (GE) voices from self-identified speakers. Human ratings found that 2 of the 6 models synthesize less similar GE voices compared to N-GE voices, and 3 have improved performance for GE voices. Automated evaluations yield conflicting results, with speaker similarity and automated mean opinion score predictors rating performance of GE voices inconsistently between models and human ratings. This highlights a potential blind spot in evaluation pipelines, emphasizing a need for more representative data and metrics that better capture human perceptual judgments. Our findings stress the need to include transgender, queer, and minority communities in creation of better datasets and model training.
查看此版本解读 →查看此版本原文 ↗