arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.01397cs.CLcs.SDeess.AS
收藏

语音转文本系统中自监督模型的性别影响研究

A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems

Avignon University(阿维尼翁大学);NAVER LABS Europe(NAVER欧洲实验室)

Marcely Zanon Boito, Laurent Besacier, Natalia Tomashenko, Yannick Estève

摘要:

用于语音处理的自监督模型最近成为语音处理管道中流行的基础模块。这些模型在未标记的音频数据上进行预训练,然后用于语音处理下游任务,例如自动语音识别(ASR)或语音翻译(ST)。由于这些模型现在被用于研究和工业系统中,因此有必要了解某些特征(如预训练数据中的性别分布)所造成的影响。使用法语作为我们的调查语言,我们训练和比较性别特定的wav2vec 2.0模型与模型包含不同程度的性别平衡,在他们的前训练数据。通过将这些模型应用于两个语音到文本的下游任务:ASR和ST进行比较。结果显示了下游集成问题的类型。我们观察到,在微调端到端ASR系统之前,使用针对性别的预训练会降低整体性能。然而,当使用自监督模型作为特征提取器时,整体ASR和ST结果遵循更复杂的模式,其中平衡的预训练模型不一定会导致最佳结果。最后,我们粗略的“公平性”指标,女性和男性测试集之间的相对性能差异,并没有显示出从平衡到性别特定的预训练wav2vec 2.0模型的强烈变化。

英文摘要:

Self-supervised models for speech processing emerged recently as popular foundation blocks in speech processing pipelines. These models are pre-trained on unlabeled audio data and then used in speech processing downstream tasks such as automatic speech recognition (ASR) or speech translation (ST). Since these models are now used in research and industrial systems alike, it becomes necessary to understand the impact caused by some features such as gender distribution within pre-training data. Using French as our investigation language, we train and compare gender-specific wav2vec 2.0 models against models containing different degrees of gender balance in their pre-training data. The comparison is performed by applying these models to two speech-to-text downstream tasks: ASR and ST. Results show the type of downstream integration matters. We observe lower overall performance using gender-specific pre-training before fine-tuning an end-to-end ASR system. However, when self-supervised models are used as feature extractors, the overall ASR and ST results follow more complex patterns in which the balanced pre-trained model does not necessarily lead to the best results. Lastly, our crude 'fairness' metric, the relative performance difference measured between female and male test sets, does not display a strong variation from balanced to gender-specific pre-trained wav2vec 2.0 models.

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。

↑