通过微调实现归一化：理解用于语音学分析的Wav2vec 2.0嵌入
Normalization through Fine-tuning: Understanding Wav2vec 2.0 Embeddings for Phonetic Analysis
AI总结：
本研究探讨wav2vec 2.0模型内部的语音归一化过程，发现微调通过选择性抑制任务无关信息有效实现归一化，且多任务微调能保留信息而不损害性能，为语音模型与人类语音感知提供新见解。
摘要：
语音归一化在语音识别与分析中起关键作用，确保从原始音频数据提取的特征具有可比性。然而，在微调预训练大型transformer模型的当前范式中，语音归一化不被视为必要步骤；相反，它在模型内部隐式执行。本研究调查transformer模型（尤其是wav2vec 2.0）内的归一化过程。通过对为各种任务微调的模型嵌入进行全面分析，结果表明，微调wav2vec 2.0通过选择性抑制与任务无关的信息，有效实现了语音归一化。我们发现，为多任务微调的模型保留了两项任务的信息而不损害性能，且抑制与任务无关的信息对有效分类并非必要。这些发现为语音模型中如何灵活实现语音归一化及其在人类语音感知中的实现方式提供了新见解。
英文摘要：
Phonetic normalization plays a crucial role in speech recognition and analysis, ensuring the comparability of features derived from raw audio data. However, in the current paradigm of fine-tuning pre-trained large transformer models, phonetic normalization is not deemed a necessary step; instead, it is implicitly executed within the models. This study investigates the normalization process within transformer models, especially wav2vec 2.0. Through a comprehensive analysis of embeddings from models fine-tuned for various tasks, our results demonstrate that fine-tuning wav2vec 2.0 effectively achieves phonetic normalization by selectively suppressing task-irrelevant information. We found that models fine-tuned for multiple tasks retain information for both tasks without compromising performance, and that suppressing task-irrelevant information is not necessary for effective classification. These findings provide new insights into how phonetic normalization can be flexibly achieved in speech models and how it is realized in human speech perception.
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。
