arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.08641cs.SDcs.CLeess.AS
收藏

ML-SUPERB 2.0:跨建模约束、语言和数据集对多语言语音模型进行基准测试

ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets

Carnegie Mellon University(卡内基梅隆大学);National Taiwan University(台湾大学);Stanford University(斯坦福大学);Toyota Technological Institute at Chicago(丰田芝加哥理工学院)

Jiatong Shi, Shih-Heng Wang, William Chen, Martijn Bartelds, Vanya Bannihatti Kumar, Jinchuan Tian, Xuankai Chang, Dan Jurafsky, Karen Livescu, Hung-yi Lee, Shinji Watanabe

AI总结:

本文提出 ML-SUPERB 2.0 基准,在多种下游模型、微调设置和高效适配方法下评估预训练 SSL 与监督语音模型,揭示模型设计、语言及数据集对多语言 ASR 性能的显著影响。

摘要:

ML-SUPERB 在语言识别和自动语音识别(ASR)任务上评估自监督学习(SSL)模型。该基准将模型视为特征提取器,并使用单一的浅层下游模型,该模型可针对下游任务进行微调。然而,真实世界的使用场景可能需要不同的配置。本文提出了 ML-SUPERB 2.0,这是一个新的基准,用于跨下游模型、微调设置和高效模型适配方法评估预训练 SSL 和监督语音模型。我们发现,相比 ML-SUPERB 的设置,性能有所提升。但是,性能取决于下游模型的设计。此外,我们发现不同语言和数据集之间存在巨大的性能差异,这表明需要更有针对性的方法来提升多语言 ASR 性能。

英文摘要:

ML-SUPERB evaluates self-supervised learning (SSL) models on the tasks of language identification and automatic speech recognition (ASR). This benchmark treats the models as feature extractors and uses a single shallow downstream model, which can be fine-tuned for a downstream task. However, real-world use cases may require different configurations. This paper presents ML-SUPERB~2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models across downstream models, fine-tuning setups, and efficient model adaptation approaches. We find performance improvements over the setup of ML-SUPERB. However, performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches to improve multilingual ASR performance.

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。

↑