输入表示，而非模型规模或预训练规模，决定说话人验证对时间退化的鲁棒性
Input Representation, Not Model Size or Pretraining Scale, Shapes Speaker Verification Robustness to Temporal Degradation
AI总结：
该研究针对自动说话人验证，发现输入表示而非模型规模或预训练规模决定其对时间退化的鲁棒性，且滤波器组输入模型的退化程度显著低于波形输入模型
摘要：
语音在严重时间退化下仍能被听众理解，但说话人身份是否能保留在很大程度上未被探索。我们评估了6个在时间完整语音上训练的自动说话人验证（ASV）模型，在三种移除不同时间线索组合的退化条件下进行测试。这些模型分为三对，每对对应一个架构家族（卷积、Transformer、Conformer），每对包含一个波形输入模型和一个梅尔滤波器组输入模型。所有模型都会退化，但鲁棒性与输入表示相关，而非预训练规模或模型大小。在所有9个家族-条件对比中，滤波器组输入模型的退化程度更低，95%置信区间中有8个不包含零，即使它比对应的波形输入模型更小或预训练更少。在受控卷积对中，模型仅在输入表示上存在差异，滤波器组输入模型的等错误率在测试的最严重退化下从1.1%上升至17.1%，而对应的波形输入模型则从2.9%上升至29.7%
英文摘要：
Speech remains intelligible to listeners under heavy temporal degradation, but whether speaker identity survives is largely unexplored. We evaluate six automatic speaker verification (ASV) models, trained on temporally intact speech, and tested under three degradations that remove different combinations of temporal cues. The models form three pairs, one per architecture family (convolutional, transformer, conformer), each pairing a waveform-input with a mel filterbank-input model. All models degrade, but robustness tracks input representation rather than pretraining scale or model size. In all nine family-by-condition comparisons the filterbank-input model degrades less, with eight of nine 95% confidence intervals excluding zero, even when it is smaller or has less pretraining than its waveform counterpart. In the controlled convolutional pair, where the models differ only in input representation, the filterbank-input model's equal error rate rises from 1.1% to 17.1% under the heaviest tested degradation, against 2.9% to29.7% for its waveform counterpart.
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。
