User interface controller for text-to-speech synthesizer

• US 5,850,629 A
• Filed: 09/09/1996
• Issued: 12/15/1998
• Est. Priority Date: 09/09/1996
• Status: Expired due to Fees

• Current Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Pearson, Steve, Holm, Frode
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/709,582
• Time in Patent Office: 827 Days
• Field of Search: 704/260, 704/270, 704/276, 704/272
• US Class Current: 704/260
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

An application-independent, text-to-speech control system which employs an easy-to-use transport from which a user can control most text-to-speech conversion functions without prior training. It provides a control means by which user designated areas may be sequentially selected, stored and played. Furthermore, moving back and forward through user-selected text may be controlled by the user, with the synthesized speech output maintaining the proper pauses and inflections.

Claims

1. A text-to-speech synthesizer for translating a plurality of discontiguous user-selected portions of text in an independent target application into an audio output that sounds like human speech, comprising:

a transport control bar;

a region store button contained on said transport control bar which when activated initiates a copy of a user-selected portion of text into one of a plurality of numerically indexed storage buffers such that said each of said plurality of numerically indexed storage buffers contains one of said plurality of discontiguous user-selected portions of text; and

a text-to-speech engine which when activated sequentially translates the discontiguous user-selected portions of text stored in said indexed storage buffers into an audio output that sounds like human speech.

2. The synthesizer of claim 1 wherein said transport control bar is configured to run under a multi-tasking operating system that provides a clipboard facility for sharing information among multiple tasks and wherein said reserved segment of memory is administered by said clipboard facility.

3. The synthesizer of claim 1 wherein said text-to-speech engine includes a parser for constructing a syntactic tree of said text contained in said text storage buffer and for performing prosodic analysis upon said tree to mark prosodic phrases.

4. The synthesizer of claim 1 wherein said text-to-speech engine includes a parser for constructing a syntactic tree of said text contained in said text storage buffer and for performing prosodic analysis upon said tree to mark prosodic phrases and further includes a pause insertion mechanism for inserting pauses in said text contained in said text storage buffer based on said marked prosodic phrases.

5. The synthesizer of claim 1 wherein said text-to-speech engine includes a parser for constructing a syntactic tree of said text contained in said text storage buffer and for performing prosodic analysis upon said tree to mark prosodic phrases and further includes an intonation selection mechanism for inserting applying an intonation curve to said text contained in said text storage buffer based on said marked prosodic phrases.

6. The synthesizer of claim 1 wherein said text-to-speech engine includes a parser for constructing a syntactic tree of said text contained in said text storage buffer and for performing prosodic analysis upon said tree to mark prosodic phrases;

and

wherein said synthesizer further comprises at least one fast wind button contained on said transport control bar for suspending generation of said audio output, jumping from a current location to a different location in said text contained in said text storage buffer and then resuming generation of said audio output using said marked prosodic phrases to affect the translation of said text contained in said text storage buffer into said audio output.

7. The synthesizer of claim 1 wherein said synthesizer generates audio output at a first speed in response to activation of said play button;

and

wherein said text-to-speech engine further includes scrub mode fast wind mechanism for moving from a current location to a different location in said text contained in said text storage buffer while generating said audio output at a speed higher than said first speed.

8. The synthesizer of claim 1 wherein said text-to-speech engine further includes scrub mode fast wind mechanism for moving from a current location to a different location in said text contained in said text storage buffer by selectively omitting words while generating said audio output.

9. The synthesizer of claim 1 wherein said user-selected portion of text is a table and wherein said synthesizer further comprising a control panel communicating with said text-to-speech engine for selectively invoking a table prosidy mode that causes said text-to-speech engine to insert pauses at predetermined locations in said table.

10. The synthesizer of claim 1 further comprising a control panel communicating with said text-to-speech engine having a speed controller for altering the speech rate produced in said audio output.

11. The synthesizer of claim 1 further comprising a control panel communicating with said text-to-speech engine having a numerical pronunciation controller for altering the way text representing numerical values are represented in said audio output.

12. The synthesizer of claim 1 wherein said text-to-speech engine includes a dictionary of words and associated phonemic data used in producing speech and wherein said synthesizer further comprising a control panel communicating with said dictionary for allowing a user to alter the phonemic data associated with selected words in said dictionary.

13. The synthesizer of claim 1 wherein said text-to-speech engine includes a dictionary of words and associated phonemic data used in producing speech and wherein said synthesizer further comprising a control panel communicating with said dictionary for allowing a user to alter the stress applied to syllables of selected words in said dictionary.

14. The synthesizer of claim 1 wherein said text-to-speech engine includes a dictionary of words and associated phonemic data used in producing speech and wherein said synthesizer further comprising a control panel communicating with said dictionary for displaying stress selection buttons adjacent individual syllables of a selected word in said dictionary, said buttons being actuable to select among different syllable stress levels to be used by said text-to-speech in generating said audio output.