Children's speech recognition is a vital, yet largely overlooked domain when
building inclusive speech technologies. The major challenge impeding progress
in this domain is the lack of adequate child speech corpora; however, recent
advances in self-supervised learning have created a new opportunity for
overcoming this problem of data scarcity. In this paper, we leverage
self-supervised adult speech representations and use three well-known child
speech corpora to build models for children's speech recognition. We assess the
performance of fine-tuning on both native and non-native children's speech,
examine the effect of cross-domain child corpora, and investigate the minimum
amount of child speech required to fine-tune a model which outperforms a
state-of-the-art adult model. We also analyze speech recognition performance
across children's ages. Our results demonstrate that fine-tuning with
cross-domain child corpora leads to relative improvements of up to 46.08% and
45.53% for native and non-native child speech respectively, and absolute
improvements of 14.70% and 31.10%. We also show that with as little as 5 hours
of transcribed children's speech, it is possible to fine-tune a children's
speech recognition system that outperforms a state-of-the-art adult model
fine-tuned on 960 hours of adult speech.

本文通过利用自监督学习采用三个儿童语音语料库构建儿童语音识别模型，分析 fine-tuning 在本地和非本地儿童语音上的性能表现和跨域儿童语料对模型性能的影响，结果显示利用跨域儿童语料进行 fine-tuning 可以使识别性能相对提高至 46.08% 和 45.53% 并且实现绝对改进 14.70% 和 31.10%，同时通过仅需要 5 个小时的儿童语音数据，也可以超越在 960 个小时成年人语音数据上进行 fine-tuning 的现有成人模型的儿童语音系统。