Back to results
US 10,319,364 B2Granted
Artificial intelligence-based text-to-speech system and method
AssigneeTelepathy Labs, Inc.
InventorsMartin Reber, Vijeta Avijeet
Life of this patent
Estimating the term…
Loading patent…
Loading patent…
AssigneeTelepathy Labs, Inc.
InventorsMartin Reber, Vijeta Avijeet
Estimating the term…
A technique improves training and speech quality of a text-to-speech (TTS) system having an artificial intelligence, such as a neural network. The TTS system is organized as a front-end subsystem and a back-end subsystem. The front-end subsystem is configured to provide analysis and conversion of text into input vectors, each having at least a base frequency, f0, a phenome duration, and a phoneme sequence that is processed by a signal generation unit of the back-end subsystem. The signal generation unit includes the neural network interacting with a pre-existing knowledgebase of phenomes to generate audible speech from the input vectors. The technique applies an error signal from the neural network to correct imperfections of the pre-existing knowledgebase of phenomes to generate audible speech signals. Speech signal specific modelling techniques in combination with applied psychoacoustic principles drive training efficiency of neural networks with positive impact on quality of generated speech signals.
A text-to-speech (TTS) system comprising:
A method of processing text-to-speech comprising:
A non-transitory computer-readable medium having program instructions which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:
Dependencies are inferred from the claim text.