发表机构
ENS; PSL university; CNRS; EHESS; Hebrew University of Jerusalem（巴黎高等师范学院; 巴黎文理研究大学; 法国国家科学研究中心; 高等社会科学研究学院; 耶路撒冷希伯来大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究构建含10种英语口音的ABX-Accent基准，用自适应域归一化微调CPC模型，在跨说话人ABX分数上平均提升23.6%，相关数据指标将开源。
AI 中文摘要
表征学习作为下游任务的预训练方法或无监督语音建模的第一步已受到广泛关注并取得良好性能，但这类方法如何处理域外语音以及如何以少样本方式适应新领域的研究较少，这对与标准口音差异较大的长尾口音语音尤为重要。我们引入基于AESRC数据集的ABX-Accent基准，包含10种英语口音，每种口音有小于10小时的未标记训练集，并将零资源挑战ABX评估指标适配到各口音。我们用自适应域归一化微调预训练的对比预测编码（CPC）模型作为基准模型，该方法先在LibriSpeech的男女分割上开发，应用于新基准时，与未适应模型相比，在跨说话人ABX分数上平均取得23.6%的相对提升，数据和指标将在论文接收后开源。
英文摘要
Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a first step towards unsu- pervised speech modeling. Yet, little is known about how such methods deal with out-of-domain speech and how could they be adapted in a few shot to new domains. This is important especially for accented speech where one observes a long tail of accents that diverge from the standard ones. We introduce ABX- Accent, a benchmark based on the AESRC dataset that features 10 different accents of English. It includes a small (< 10 hours) unlabelled training set in each of the accents and adaptations of the Zero Resources Challenge ABX evaluation metrics to each of the accents. We illustrate this benchmark with a baseline model that uses adaptive domain normalization to fine tune a pretrained Contrastive Predictive Coding model on the accents. This method is first developed on LibriSpeech using a male/female split. When applied to the new benchmark, the proposed method yields a relative improvement of 23.6% on across-speaker ABX scores on average compared to non adapted models. The data and metrics will be open sourced upon paper acceptance
