“AI in this sense means using Machine Learning (ML)/Neural Networks (NN) to convert the text (or phonemes) to audio. There are effectively two approaches to voice synthesis: time-domain and pitch-domain. In time-domain synthesis you care concatenating short waveforms together. These are variations of Overlap and Add: OLA [1], PSOLA [2], MBROLA [3], etc. …”
WaveGrad: Estimating Gradients for Waveform Generation
This paper introduces WaveGrad, a conditional model for waveform generation which estimates gradients of the data density. The model is built on prior work on score matching and diffusion probabilistic models. It starts from a Gaussian white noise signal and iteratively refines the signal via a gradient-based sampler conditioned on the mel-spectrogram. WaveGrad offers a natural way to trade inference speed for sample quality by adjusting the number of refinement steps, and bridges the gap between non-autoregressive and autoregressive models in terms of audio quality. We find that it can generate high fidelity audio samples using as few as six iterations. Experiments reveal WaveGrad to generate high fidelity audio, outperforming adversarial non-autoregressive baselines and matching a strong likelihood-based autoregressive baseline using fewer sequential operations. Audio samples are available at https://wavegrad.github.io/.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及- WaveGrad: Estimating Gradients for Waveform Generation ↗colinprince · 2020-09-11 · 3 分
- Estimating Gradients for Waveform Generation [pdf] ↗colinprince · 2020-09-15 · 2 分