Generating acoustic sequences via neural networks using combined prosody info
AssigneeInternational Business Machines Corporation
InventorVyacheslav Shechtman
Life of this patent
Estimating the term…
Abstract
An example system includes a processor to receive a linguistic sequence and a prosody info offset. The processor can generate, via a trained prosody info predictor, combined prosody info including a number of observations based on the linguistic sequence. The number of observations include linear combinations of statistical measures evaluating a prosodic component over a predetermined period of time. The processor can generate, via a trained neural network, an acoustic sequence based on the combined prosody info, the prosody info offset, and the linguistic sequence.
Claims20
A system, comprising a processor to:
- receive a linguistic sequence and a prosody info offset;
- generate, via a trained prosody info predictor, combined prosody info comprising a plurality of observations based on the linguistic sequence, wherein the plurality of observations comprise linear combinations of statistical measures evaluating a prosodic component over a predetermined period of time;
- and
- generate, via a trained neural network, an acoustic sequence based on the combined prosody info, the prosody info offset, and the linguistic sequence.
A computer-implemented method, comprising:
- receiving a linguistic sequence and a prosody info offset;
- generating, via a trained prosody info predictor, combined prosody info comprising a plurality of observations based on and aligned to the linguistic sequence, wherein the plurality of observations comprise linear combinations of statistical measures evaluating a prosodic component over a predetermined period of time;
- and
- generating, via a trained neural network, an acoustic sequence based on the combined prosody info, the prosody info offset, and the linguistic sequence.
A computer program product for automatically controlling prosody, the computer program product comprising a computer-readable storage medium having program code embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program code executable by a processor to cause the processor to:
- receive a linguistic sequence and a prosody info offset;
- generate combined prosody info comprising a plurality of observations based on the linguistic sequence, wherein the plurality of observations comprise linear combinations of statistical measures evaluating a prosodic component over a predetermined period of time;
- and
- generate an acoustic sequence based on the combined prosody info, the prosody info offset, and the linguistic sequence.
Dependencies are inferred from the claim text.