用120毫秒窗口实现跨语言通用音素编码，无需上下文
CUPE: Contextless Universal Phoneme Encoder for Language-Agnostic Speech Processing
- 基于音素级时长窗口的独立处理，轻量化设计
- 在多语言数据上达到与主流方法相当的跨语言性能
- 适合需要纯净音素表示的语音任务，如跨语言语音识别
通用音素识别通常需分析长语音段和语言特定模式。许多语音处理任务需要不受上下文影响的纯音素表示，这促使我们开发了CUPE——一种轻量级模型，仅需120毫秒（约一个音素长度）即可捕捉关键音素特征。CUPE独立处理短而固定的时窗，尽管参数量少于现有方法，仍通过学习所有语言共有的基础声学模式，实现了具有竞争力的跨语言表现。我们在多种语言上进行了监督与自监督训练，并在UCLA语音语料库上进行零样本测试，结果表明其具备强大的跨语言泛化能力，证明通过建模音素级时窗内的基本声学模式，可实现有效的通用语音处理。
原文摘要 · Abstract (English)
Universal phoneme recognition typically requires analyzing long speech segments and language-specific patterns. Many speech processing tasks require pure phoneme representations free from contextual influence, which motivated our development of CUPE - a lightweight model that captures key phoneme features in just 120 milliseconds, about one phoneme's length. CUPE processes short, fixed-width windows independently and, despite fewer parameters than current approaches, achieves competitive cross-lingual performance by learning fundamental acoustic patterns common to all languages. Our extensive evaluation through supervised and self-supervised training on diverse languages, including zero-shot tests on the UCLA Phonetic Corpus, demonstrates strong cross-lingual generalization and reveals that effective universal speech processing is possible through modeling basic acoustic patterns within phoneme-length windows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。