LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis — mentioned by PieSquared

Wed, 28 Aug 2019 19:52:57 GMT

There's a few recent papers actually that show minor improvements by integrating LPC prediction into deep methods ([0], [1]). In my experience (some of which comes from reproducing these, some of which comes from my own experiments), this isn't actually too useful, at at most offers a minor modeling benefit. The main difference between something like Festival and what we have now is the amount of domain-specific engineering. (This is generally the promise of deep learning -- replace hand-engineered features with simple-to-understand features and a deep model.) If you go and read the Festival…

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

LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis · HackerPapers discussions

LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis — mentioned by PieSquared