Autovocoder：使用可微数字信号处理从学习到的语音表示中快速生成波形
Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing
AI总结：
提出autovocoder，利用机器学习获得语音表示，并通过可微DSP操作快速反演生成波形，速度优于Griffin-Lim和HiFi-GAN且质量相当。
摘要：
大多数最先进的文本转语音系统使用mel-spectrogram作为中间表示，将任务分解为声学建模和波形生成。mel-spectrogram通过简单、快速的DSP操作从波形中提取，但从mel-spectrogram生成高质量波形需要计算成本高昂的机器学习：neural vocoder。我们提出的“autovocoder”反转了这种安排。我们使用机器学习获得一种替代mel-spectrogram的表示，并可通过包含inverse STFT的可微实现等简单、快速的操作将其反转为波形。autovocoder生成波形的速度比基于DSP的Griffin-Lim算法快5倍，比neural vocoder HiFi-GAN快14倍。我们提供了感知听力测试结果，证实语音质量在copy synthesis任务中与HiFi-GAN相当。
英文摘要：
Most state-of-the-art Text-to-Speech systems use the mel-spectrogram as an intermediate representation, to decompose the task into acoustic modelling and waveform generation. A mel-spectrogram is extracted from the waveform by a simple, fast DSP operation, but generating a high-quality waveform from a mel-spectrogram requires computationally expensive machine learning: a neural vocoder. Our proposed ``autovocoder'' reverses this arrangement. We use machine learning to obtain a representation that replaces the mel-spectrogram, and that can be inverted back to a waveform using simple, fast operations including a differentiable implementation of the inverse STFT. The autovocoder generates a waveform 5 times faster than the DSP-based Griffin-Lim algorithm, and 14 times faster than the neural vocoder HiFi-GAN. We provide perceptual listening test results to confirm that the speech is of comparable quality to HiFi-GAN in the copy synthesis task.
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。
