论文标题
70种语言的大量多语言ASR：令牌化，体系结构和概括功能
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities
论文作者
论文摘要
端到端的多语言ASR变得更具吸引力，因为诸如简化培训和部署过程以及从高资源到低资源语言的积极绩效转移等原因。但是，扩大语言数量，总小时数和唯一令牌的数量并不是一项琐碎的任务。本文探讨了70种语言上的大规模多语言ASR模型。我们检查两个体系结构：（1）共享嵌入和输出以及（2）多个嵌入和输出模型。在共享模型实验中，我们展示了跨不同语言的令牌化策略的重要性。后来，我们使用最佳的令牌化策略来训练多个嵌入和输出模型，以进一步改善我们的结果。与单语模型相比，我们的多语言ASR达到13.9％-15.6％的平均相对改善。我们表明，我们的多语言ASR在一个看不见的数据集和域上很好地概括了，在多语言库佩（MLS）上分别获得了9.5％和7.5％的WER，分别以零射击和命名。
End-to-end multilingual ASR has become more appealing because of several reasons such as simplifying the training and deployment process and positive performance transfer from high-resource to low-resource languages. However, scaling up the number of languages, total hours, and number of unique tokens is not a trivial task. This paper explores large-scale multilingual ASR models on 70 languages. We inspect two architectures: (1) Shared embedding and output and (2) Multiple embedding and output model. In the shared model experiments, we show the importance of tokenization strategy across different languages. Later, we use our optimal tokenization strategy to train multiple embedding and output model to further improve our result. Our multilingual ASR achieves 13.9%-15.6% average WER relative improvement compared to monolingual models. We show that our multilingual ASR generalizes well on an unseen dataset and domain, achieving 9.5% and 7.5% WER on Multilingual Librispeech (MLS) with zero-shot and finetuning, respectively.
