LAMA-UT：通过正字法统一与语言特定音译实现语言无关的多语言自动语音识别
LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration
AI总结：
提出LAMA-UT，一种无需语言特定模块的多语言ASR流水线，通过正字法统一和音译转换，以极少训练数据达到与Whisper和MMS相当的性能，错误率相对降低45%。
摘要：
构建一个能够在不同语言间公平表现的通用多语言自动语音识别（ASR）模型，由于其固有的困难，长期以来一直是一项挑战。为了解决这一问题，我们提出了一种通过正字法统一与语言特定音译实现语言无关的多语言ASR流水线（LAMA-UT）。LAMA-UT在无需任何语言特定模块的情况下运行，同时匹配了在极少量数据上训练的最先进模型的性能。我们的流水线包含两个关键步骤。首先，我们利用一个通用转录生成器将正字法特征统一为罗马化形式，并捕获不同语言间的共同语音特征。其次，我们利用一个通用转换器将这些通用转录转换为语言特定的转录。在实验中，我们展示了所提方法利用通用转录进行大规模多语言ASR的有效性。与Whisper相比，我们的流水线实现了45%的相对错误率降低，并且尽管仅使用了Whisper训练数据的0.1%进行训练，其性能与MMS相当。此外，我们的流水线不依赖任何语言特定模块，但其性能与利用额外语言特定词典和语言模型的零样本ASR方法相当。我们期望这一框架能够成为灵活的多语言ASR系统的基石，该系统甚至可泛化到未见过的语言。
英文摘要：
Building a universal multilingual automatic speech recognition (ASR) model that performs equitably across languages has long been a challenge due to its inherent difficulties. To address this task we introduce a Language-Agnostic Multilingual ASR pipeline through orthography Unification and language-specific Transliteration (LAMA-UT). LAMA-UT operates without any language-specific modules while matching the performance of state-of-the-art models trained on a minimal amount of data. Our pipeline consists of two key steps. First, we utilize a universal transcription generator to unify orthographic features into Romanized form and capture common phonetic characteristics across diverse languages. Second, we utilize a universal converter to transform these universal transcriptions into language-specific ones. In experiments, we demonstrate the effectiveness of our proposed method leveraging universal transcriptions for massively multilingual ASR. Our pipeline achieves a relative error reduction rate of 45% when compared to Whisper and performs comparably to MMS, despite being trained on only 0.1% of Whisper's training data. Furthermore, our pipeline does not rely on any language-specific modules. However, it performs on par with zero-shot ASR approaches which utilize additional language-specific lexicons and language models. We expect this framework to serve as a cornerstone for flexible multilingual ASR systems that are generalizable even to unseen languages.
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。
