The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to overcome such data scarcity. The SpeechBlender utilizes varieties of masks to target different regions of phonetic units, and use the mixing factors to linearly interpolate raw speech signals while augmenting pronunciation. The masks facilitate smooth blending of the signals, generating more effective samples than the `Cut/Paste' method. Our proposed technique achieves state-of-the-art results, with Speechocean762, on ASR dependent mispronunciation detection models at phoneme level, with a 2.0% gain in Pearson Correlation Coefficient (PCC) compared to the previous state-of-the-art [1]. Additionally, we demonstrate a 5.0% improvement at the phoneme level compared to our baseline. We also observed a 4.6% increase in F1-score with Arabic AraVoiceL2 testset.

翻译：摘要：缺乏标注的第二语言（L2）语音数据是设计发音错误检测模型的主要挑战。我们提出SpeechBlender——一种细粒度的数据增强流水线，用于生成发音错误以克服此类数据稀缺问题。SpeechBlender利用多种掩码针对语音单元的不同区域，并通过混合因子对原始语音信号进行线性插值，同时增强发音。这些掩码能够平滑地混合信号，生成比“剪切/粘贴”方法更有效的样本。我们提出的技术在Speechocean762数据集上达到了最优结果，在音素级别上，ASR依赖的发音错误检测模型的皮尔逊相关系数（PCC）相比先前最优方法[1]提升了2.0%。此外，我们展示了在音素级别上相比基线模型5.0%的提升。我们还观察到在阿拉伯语AraVoiceL2测试集上F1分数提升了4.6%。