基于对抗训练的连续声压级控制的人声强度转换
Vocal Intensity Conversion with Continuous SPL Control via Adversarial Training
AI总结：
本文提出一种基于对抗训练的连续声压级控制的人声强度转换方法，采用条件循环一致GAN，对比三种语音表征，实现了目标强度变化83%的转换效果，验证了感知强度随目标水平升高而增加。
摘要：
人声强度转换是指在保留语音内容和说话人身份的前提下，将录制的语音转换为不同人声强度，而非简单缩放其振幅。现有系统通过参考语音或少数离散类别控制强度，而本文采用连续分贝（dB）尺度上的任意目标声压级（SPL）控制转换。我们训练了一个轻量型转换器，该转换器为条件循环一致生成对抗网络（conditional cycle-consistent GAN），无需平行数据，用于转换冻结语音编码器的特征，预训练声码器（pretrained vocoder）基于该特征重合成语音。我们对比了三种表征：对数梅尔频谱图、WavLM和SpeechTokenizer，并引入客观协议，在校准语料库上测量实际强度变化与目标强度变化的差距。采用WavLM时，该转换器实现了目标强度变化的83%，同时还改变了基频。感知评估证实，在振幅归一化的刺激下，感知人声强度随目标水平升高而增加。
英文摘要：
Vocal intensity conversion renders a recorded utterance at a different vocal intensity, rather than simply scaling its amplitude, while preserving its content and speaker identity. Existing systems control intensity through a reference utterance or a few discrete categories. Instead, we control the conversion with any target sound pressure level (SPL) on a continuous dB scale. A lightweight converter, trained as a conditional cycle-consistent GAN without parallel data, transforms the features of a frozen speech encoder, from which a pretrained vocoder resynthesizes the speech. We compare three representations, log-mel spectrograms, WavLM, and SpeechTokenizer, and introduce an objective protocol that measures the achieved intensity change against the target one on a calibrated corpus. With WavLM, the converter achieves a measured 83% of the target change in intensity and also shifts the fundamental frequency. A perceptual evaluation confirms that perceived vocal intensity increases with the target level on amplitude-normalized stimuli.
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。
