发表机构
University of Illinois Urbana-Champaign; Wuhan University（伊利诺伊大学厄巴纳-香槟分校; 武汉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究语音增强对自动语音识别的影响，提出推理时间极坐标投影诊断方法，通过扫描控制参数将ASR退化转化为幅度和相位效应，分析得出幅度强度是关键，最佳强度因识别器而异，该投影可为SE前端提供简单缓解方法。
AI 中文摘要
语音增强（SE）可显著提升感知质量，但增强后的语音不一定能提高自动语音识别（ASR）。现有补救措施可缓解这种不匹配，但常见解释仍停留在定性层面。我们提出推理时间极坐标投影，用于STFT域增强诊断。给定掩码\(M = Ae^{j\phi}\)，极坐标投影形成\(M_{\alpha,\gamma}=A^\alpha e^{j\gamma\phi}\)。通过在冻结的SE和ASR模型上扫描这些控制参数，将ASR退化转化为可测量的幅度和相位效应。投影分析表明幅度强度是关键因素，估计的相位校正并无识别优势。最佳幅度强度取决于识别器，波形输入的wav2vec2.0偏好强校正，而对数梅尔输入、抗噪的Whisper则偏好较弱校正。最后，该投影为STFT掩码域中的任何SE前端提供了一种无需重新训练增强器或识别器的简单缓解方法，对依赖增强语音的语音助手和智能体直接有用。
英文摘要
Speech enhancement (SE) can substantially improve perceptual quality, yet enhanced speech does not necessarily improve automatic speech recognition (ASR). Common explanations such as enhancement artifacts and over-suppression remain qualitative and do not localize which enhancement component affects recognition. We study inference-time polar projection, which transforms an STFT mask $M=Ae^{jϕ}$ into $M_{α,γ}=A^αe^{jγϕ}$ and independently varies magnitude strength and estimated phase correction with frozen SE and ASR models. The resulting response curves separate effects that are coupled in ordinary enhanced-vs-noisy comparisons. On VoiceBank+DEMAND with FRCRN, wav2vec2.0 improves from 17.13 to 10.20 WER near full magnitude correction ($α=.85$), while Whisper reaches its best WER under much weaker correction, improving from 6.44 to 5.57 at $α=.25$ and returning to 6.46 at full magnitude. A second enhancer, a robustness-oriented ASR model, and a reverberant WSJ0 mixture set generalize the pattern and show that the preferred magnitude region depends on the recognizer and acoustic condition. Estimated phase correction is not a stable ASR lever in these evaluations: its effect is smaller, setting-dependent, and provides no consistent gain once magnitude strength is fixed.
