WaveGrad: Estimating Gradients for Waveform Generation · HackerPapers discussions

WaveGrad: Estimating Gradients for Waveform Generation — mentioned by rhdunn

Sat, 24 Jan 2026 11:28:41 GMT

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. In pitch-domain synthesis, the analysis and synthesis happens in the pitch domain through the Fast Fourier Transform (visualized as a spectrogram [4]), often adjusted to the Mel scale [5] to better highlight the pitches and overtones. The TTS…

Paper and discussion history. A mention is not an endorsement.

WaveGrad: Estimating Gradients for Waveform Generation — HN submission

Tue, 15 Sep 2020 02:43:32 GMT

Estimating Gradients for Waveform Generation [pdf]

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

WaveGrad: Estimating Gradients for Waveform Generation — HN submission

Fri, 11 Sep 2020 13:17:57 GMT

WaveGrad: Estimating Gradients for Waveform Generation

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.