Method for generating audio renderings of digitized works having highly technical content

• US 5,572,625 A
• Filed: 10/22/1993
• Issued: 11/05/1996
• Est. Priority Date: 10/22/1993
• Status: Expired due to Term

• Current Assignee: Cornell Research Foundation Incorporated (Cornell University)
• Original Assignee: Cornell Research Foundation Incorporated (Cornell University)
• Inventors: Gries, David, Raman, T. V.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): GROVER, JOHN M
• Application Number:
  US08/141,348
• Time in Patent Office: 1,110 Days
• Field of Search: 395/2.68, 395/2.69, 395/2.75, 395/2.79, 395/2.8, 395/2.87, 434/112, 434/116, 434/128
• US Class Current: 704/260
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

The present invention provides a method for producing auditory renderings of digitized works and, in particular, digitized documents containing complex mathematical expressions. Documents are first entered into a computer system and formatted with a markup language, such as one of the TeX® or LaTeX® family of languages. The formatted documents are parsed to provide a tree-structured, high-level representation. Mathematical expressions are in quasi-prefix form. Lexical analysis and recognition processes are then undertaken. The resulting analyzed documents are provided to an audio output device (such as a voice synthesizer) operating under control of a set of predetermined rendering rules. The resultant audio signal contains not only textual content but also the analogical markings produced by the reading rules. Multichannel audio outputs may be used to allow for spatial placement capability, in addition to the other analogical markings. An audio formatting language (AFL) is provided to allow for manipulation of rendering rules. A browsing capability is also provided to allow a listener to easily locate his or her place in a document.

Claims

1. A method of auditorially rendering mathematical expressions, formulas, tables, documents and language, comprising the steps of:

a) formatting mathematical information to be auditorially rendered;

b) transforming the mathematical information of step (a) into a structured representation having the form of a hierarchical tree; and

c) using an audio language and rendering rules for operating on the structured representation of the mathematical information of step (b) to produce an audio output, comprising stereo, multivoice parameters, including parameters for adjusting respective left and right volumes.

2. The method of claim 1, wherein the transforming of the mathematical information into a structured representation in accordance with step (b) comprises transforming math objects of the hierarchical tree to a quasi-prefix form.

3. The method of claim 2, wherein math objects are provided with six attribute locations.

4. The method of claim 3, wherein at least one of said six attributes is itself provided with an attribute.

5. The method of claim 1, wherein mathematical notation of said mathematical information of step (b) is assigned precedence levels.

6. The method of claim 1, wherein mathematical information formatted in accordance with step (a) has been marked up in TeX®

.

7. The method of claim 1, wherein the audio output of step (c) comprises multivoice parameters including speech rate, volume, voice quality, pitch and intonation.

8. The method of claim 1, wherein the audio output of step (c) comprises stereo multivoice parameters, consisting of left and right volume.

9. The method of claim 1, wherein the audio output of step (c) comprises spatial effects.

10. The method of claim 1, further comprising the step of:

d) interactively operating on said audio output.

11. The method of claim 1, further comprising the step of:

d) browsing through said audio output.

12. The method of claim 1, wherein the audio output of step (c) comprises fleeting and persistent cues.

13. The method of claim 1, wherein the audio output of step (c) comprises recursive substitutions.

14. A method of auditorially rendering mathematical expressions, formulas, tables, documents and language, comprising the steps of:

a) formatting mathematical information to be auditorially rendered, using a mark-up language;

b) transforming the mathematical information of step (a) into a structured representation having the form of a hierarchical tree by projecting mathematical expressions into two-dimensional information, and annotating this structure with attributes; and

c) using an audio language and rendering rules for operating on the structured representation of the mathematical information of step (b), to produce a stereophonic, audio output.

15. The method of claim 14, wherein at least one of the attributes of step (b) itself contains a tree structure.

16. The method of claim 14, wherein said transforming step (b) uses recursive substitutions.

17. A method of auditorially rendering mathematical expressions, formulas, tables, documents and language, comprising the steps of:

a) formatting mathematical information to be auditorially rendered using a mark-up language;

b) transforming the mathematical information of step (a) into a structured representation having the form of a hierarchical tree;

c) using an audio language and rendering rules for operating on the structured representation of the mathematical information of step (b), to produce a stereophonic, audio output;

d) listening to the stereophonic, audio output of step (c); and

e) interactively traversing said stereophonic, audio output.