在非洲语言上扩展HuBERT：从基础到大模型和XL
Scaling HuBERT for African Languages: From Base to Large and XL
AI总结：
本研究提出SSA-HuBERT-Large和SSA-HuBERT-XL两种大模型，专注于非洲语音，通过实验验证了更大模型在语音识别和语言识别任务中的性能提升。
摘要：
尽管在多语言语音处理方面取得了近期进展，非洲语言在研究和部署系统中仍然代表性不足，尤其是在强、开放权重编码器在低资源监督下转移效果良好的情况下。自监督学习在这样的情况下已被证明特别有前途，但大多数公开发布的针对非洲语音的模型仍停留在基础规模，留下了一个未解的问题：是否仅在非洲中心的音频上训练的更大编码器能带来实质性的收益，以及模型容量如何与数据组成相互作用。本工作通过引入SSA-HuBERT-Large（317M参数）和SSA-HuBERT-XL（964M参数），即第一个仅在非洲语音上训练的大模型，以及基础规模的对应模型，填补了这一空白。我们释放这些模型作为开放权重：见https://huggingface.co/collections/Orange/african-speech-foundation-models。通过进行一项专注于撒哈拉以南语言的精心控制的实验研究，涵盖自动语音识别（ASR）和语言识别（LID）任务，我们证明了更大架构通过有效利用大规模音频数据集显著提高了性能。
英文摘要：
Despite recent progress in multilingual speech processing, African languages remain under-represented in both research and deployed systems, particularly when it comes to strong, open-weight encoders that transfer well under low-resource supervision. Self-supervised learning has proven especially promising in such settings, yet most publicly released models targeting African speech remain at BASE scale, leaving unanswered whether larger encoders, trained exclusively on Africa-centric audio, offer tangible benefits and how model capacity interacts with data composition. This work addresses that gap by introducing SSA-HuBERT-Large (317M parameters) and SSA-HuBERT-XL (964M parameters), the first large models trained solely on African speech, alongside a BASE size counterpart. We release these models as open weights: see https://huggingface.co/collections/Orange/african-speech-foundation-models. By conducting a carefully controlled experimental study focused exclusively on Sub-Saharan languages, covering automatic speech recognition (ASR) and language identification (LID) tasks, we demonstrate that larger architectures significantly improve performance by effectively leveraging large audio datasets.
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。
