Systems and methods for providing non-lexical cues in synthesized speech
AssigneeIntel Corporation
InventorsJessica M. Christian, Peter Graff, Crystal A. Nakatsu, Beth Ann Hockey
Life of this patent
Estimating the term…
Abstract
Systems and methods for providing non-lexical cues in synthesized speech are described herein. Original text is analyzed to determine characteristics of the text and/or to derive or augment an intent (e.g., an intent code). Non-lexical cue insertion points are determined based on the characteristics of the text and/or the intent. One or more nonlexical cues are inserted at insertion points to generate augmented text. The augmented text is synthesized into speech, including converting the non-lexical cues to speech output.
Claims25
A system that converts text to speech, the system comprising:
- an intent analyzer to analyze by one or more processors original text received by the system to derive an intent representative of intended meaning to be conveyed by non-lexical cues;
- a non-lexical cue insertion engine to determine by the one or more processors insertion points of non-lexical cues based on the derived intent and to insert a non-lexical cue at the insertion point within the original text to generate augmented text;
- and
- a speech synthesizer to synthesize speech from the augmented text.
A computer-implemented method of converting text to speech, the method comprising:
- analyzing, on one or more computing devices, original text to derive an intent representative of intended meaning of the original text that can be conveyed by non-lexical cues;
- determining, on the one or more computing devices, an insertion point of a non-lexical cue, in the original text, based on the derived intent;
- inserting by the one or more computing devices a non-lexical cue at the insertion point within the original text to generate augmented text;
- and
- synthesizing speech from the augmented text.
At least one non-transitory computer-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to perform operations to convert text to speech, comprising:
- analyzing original text to derive an intent representative of intended meaning to be conveyed by one or more non-lexical cues;
- determining an insertion point of a non-lexical cue based on the derived intent;
- inserting a non-lexical cue at the insertion point within the original text to generate augmented text;
- and
- synthesizing speech from the augmented text.
Dependencies are inferred from the claim text.