Loading patent…
AssigneeBaidu USA LLC
InventorsSercan O. Arik, Gregory Diamos, Andrew Gibiansky, John Miller, Kainan Peng, Wei Ping, Jonathan Raiman, Yanqi Zhou
Estimating the term…
Described herein are systems and methods for augmenting neural speech synthesis networks with low-dimensional trainable speaker embeddings in order to generate speech from different voices from a single model. As a starting point for multi-speaker experiments, improved single-speaker model embodiments, which may be referred to generally as Deep Voice 2 embodiments, were developed, as well as a post-processing neural vocoder for Tacotron (a neural character-to-spectrogram model). New techniques for multi-speaker speech synthesis were performed for both Deep Voice 2 and Tacotron embodiments on two multi-speaker TTS datasets—showing that neural text-to-speech systems can learn hundreds of unique voices from twenty-five minutes of audio per speaker.
A computer-implemented method for synthesizing speech from text, comprising:
A non-transitory computer-readable medium or media comprising one or more sequences of instructions which, when executed by at least one processor, causes steps for synthesizing speech from text, comprising:
A system for synthesizing speech from text comprising:
Dependencies are inferred from the claim text.