arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.27273cs.SD
收藏

少样本合成方言语音用于ASR微调:什么有助于什么?

Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

University of Washington(华盛顿大学)

Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson, Dilek Hakkani-Tür, Volodymyr Kindratenko

AI总结:

研究比较了合成方言语音在ASR微调中的有效性,发现随机音素扰动比目标方言音素编辑更有效,且真实语音与合成语音混合可稳定低资源微调。

摘要:

合成方言语音是一种在真实方言录音稀缺时提升自动语音识别(ASR)性能的有希望的方法。我们探讨了什么使此类数据对ASR微调有用:目标方言音素编辑暴露识别器于方言特定发音,或随机音素扰动在音素空间中充当增强。在少样本TTS流程中,我们比较了LLM生成的方言编辑与匹配速率的随机替换和oracle控制,使用真实方言音素和语调。随机替换恢复了大部分ASR增益:LLM目标方言编辑仅比随机替换略好,真实音素接近随机基线并随着合成ASR微调集增大接近它,添加真实语调仅带来小幅增益。混合合成与真实方言语音也稳定了低资源微调,但固定合成预算后期会稀释真实数据信息,显示真实-合成比例的重要性。

英文摘要:

Synthetic accented speech is a promising way to improve automatic speech recognition (ASR) when real accented recordings are scarce. We ask what makes such data useful for ASR fine-tuning: target-accent phoneme edits that expose the recognizer to accent-specific pronunciations, or random phoneme perturbations that act as augmentation in phoneme space. In a few-shot TTS pipeline, we compare LLM-generated accent edits with matched-rate random substitutions and oracle controls using ground-truth accented phonemes and prosody. Random substitutions recover much of the ASR gain: LLM target-accent edits improve over random by only a small margin, ground-truth phonemes stay close to the random baseline and nearly converge with it as the synthetic ASR fine-tuning set grows larger, and adding ground-truth prosody yields only a modest further gain. Mixing synthetic with real accented speech also stabilizes low-resource fine-tuning, but a fixed synthetic budget can later dilute the information in real data, showing that the real--synthetic ratio matters.

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。

↑