神经音频编解码器传输下说话人验证性能权衡分析
Analysis of Speaker Verification Performance Trade-offs with Neural Audio Codec Transmission
AI总结：
该研究分析不同比特率下传统与神经音频编解码器对说话人验证性能的影响，发现神经编解码器在低带宽下更优，高比特率略逊于Opus，验证了其作为传统编解码器替代方案的可行性。
摘要：
神经音频编解码器（Neural audio codecs, NACs）近年来取得了显著进展，正迅速被应用于众多音频处理流水线中。但这类编解码器可能引入音频失真，进而降低说话人验证（speaker verification, SV）的性能。本研究探究了不同比特率下的传统音频编解码器与神经音频编解码器，对在VoxCeleb1数据集上评估的三个前沿SV模型的影响。研究结果显示，随着比特率降低，所有模型和编解码器下的SV性能均出现一致下降。值得注意的是，与传统编解码器相比，NACs并不会从根本上破坏SV性能。在低比特率（<12 kbps）下，NACs的表现比Opus优6-8%；在较高比特率（约24 kbps）下仅略微落后，等错误率（EER）仅上升0.4-0.7%。高比特率下的这种差距，可能是因为NACs主要针对感知质量优化，会不经意间丢弃关键的说话人区分特征，而Opus的设计目标则是保留人声特征。本研究表明，NACs是传统编解码器的可行替代方案，尤其在带宽受限的场景下。为弥补高比特率下的性能差距，未来工作应聚焦于开发具备说话人感知能力的NACs，或是对SV模型进行重训练与适配。
英文摘要：
Neural audio codecs (NACs) have made significant advancements in recent years and are rapidly being adopted in many audio processing pipelines. However, they can introduce audio distortions which degrade speaker verification (SV) performance. This study investigates the impact of both traditional and neural audio codecs at varying bitrates on three state of-the-art SV models evaluated on the VoxCeleb1 dataset. Our findings reveal a consistent degradation in SV performance across all models and codecs as bitrates decrease. Notably, NACs do not fundamentally break SV performance when compared to traditional codecs. They outperform Opus by 6-8% at low-bitrates (< 12 kbps) and remain marginally behind at higher bitrates ($\approx$ 24 kbps), with an EER increase of only 0.4-0.7%. The disparity at higher bitrates is likely due to the primary optimization of NACs for perceptual quality, which can inadvertently discard critical speaker-discriminative features, unlike Opus which was designed to preserve vocal characteristics. Our investigation suggests that NACs are a feasible alternative to traditional codecs, especially under bandwidth limitations. To bridge the gap at higher bitrates, future work should focus on developing speaker-aware NACs or retraining and adapting SV models.
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。
