Hypertext navigation system controlled by spoken words

• US 6,029,135 A
• Filed: 11/14/1995
• Issued: 02/22/2000
• Est. Priority Date: 11/14/1994
• Status: Expired due to Term

• Current Assignee: Tamiras Per Pte Ltd LLC (Intellectual Ventures LLC)
• Original Assignee: Siemens AG
• Inventors: Krasle, Darin Edward
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/557,525
• Time in Patent Office: 1,561 Days
• Field of Search: 395/2.79, 395/2.84, 395/2.75, 395/2.81, 395/2.85, 395/2.44, 704/270, 704/272, 704/275, 704/276, 704/235, 704/243, 704/239, 704/240, 704/249, 704/254, 704/260, 704/231, 704/246, 704/251, 704/257, 704/252
• US Class Current: 704/275
• CPC Class Codes: G06F 16/748 Hypervideo linking data to content, e.g. by linking an URL to a video object in the context of video distribution systems H04N21/858
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A hypertext navigation system that is controllable by spoken words have hypertext documents to which specific dictionaries and probability models for assisting in an acoustic voice recognition of hyper-links of this hypertext document are allocated. Control of a hypertext viewer or, respectively, browser and navigation in the hypertext document or hypertext system by pronouncing links is provided. The voice recognition is thereby optimally adapted to the links to be recognized without these having to be previously known.

Claims

1. A hypertext navigation system controllable by spoken words, comprising:

a means for recognizing spoken language; and

means for adapting said means for recognizing spoken language to contents of potentially unknown words of hypertext documents so as to effect navigation by hypertext elements in said hypertext documents, including;

means for allocating spoken words to corresponding ones of said hypertext elements.

2. A hypertext document for use with a system for recognizing spoken language, comprising:

hypertext character sequences for hypertext navigation in said hypertext document, said hypertext character sequences being potentially unknown words to said system for recognizing spoken language; and

further data in said hypertext document, said further data including spoken language elements corresponding to said hypertext character sequences for assisting said system for recognizing spoken language in recognition of spoken words that correspond to said hypertext character sequences of said hypertext document and in activation of corresponding hypertext navigation functions.

3. A hypertext document according to claim 2, wherein said further data include a dictionary and a probability model, said dictionary containing said hypertext character sequences of said hypertext document and phoneme sequences allocated to said hypertext character sequences as dictionary entries, and wherein said probability model includes probabilities for matching said phoneme sequences to spoken words of a user to make it possible for said system for recognizing spoken language of a user to allocate a spoken word or a sequence of spoken words to an entry of said dictionary.

4. A hypertext navigation system controllable by spoken words, comprising:

a means for recognizing spoken language;

means for adapting said means for recognizing to potentially unknown words of hypertext documents, including

hypertext character sequences being the potentially unknown words for hypertext navigation in said hypertext document; and

further data in said hypertext document including a set of acceptable spoken words corresponding to said hypertext character sequences, said further data assisting said system for recognizing spoken language in recognition of spoken words of a user that correspond to said hypertext character sequences of said hypertext document and in activating hypertext navigation functions corresponding to said hypertext character sequences.

5. A hypertext navigation system controllable by spoken words, comprising:

a means for recognizing spoken language;

means for adapting said means for recognizing to potentially unknown words of hypertext documents, including

hypertext character sequences being the potentially unknown words for hypertext navigation in said hypertext document; and

further data in said hypertext document, said further data assisting said system for recognizing spoken language in recognition of spoken words that correspond to said hypertext character sequences of said hypertext document, wherein said further data include a dictionary and a probability model, said dictionary containing said hypertext character sequences identified from said hypertext document and phoneme sequences allocated to said hypertext character sequences as entries in said dictionary, and wherein said probability model makes it possible for said system for recognizing spoken language of a user to allocate a spoken word or a sequence of spoken words to an entry of said dictionary and activate a function corresponding to said hypertext character sequence.

6. A hypertext navigation system controllable by spoken words as claimed in claim 5, whereby said dictionary and said probability model allocated to a hypertext document or to a part of a hypertext document are produced at run time as said hypertext document is open, and the voice recognition system is reconfigured at run time.

7. A hypertext navigation system controllable by spoken words as claimed in claim 5, whereby, based on definition of a user, said dictionaries and said probability models that have been produced for at least portions of hypertext documents which have been already at least partially opened and displayed are stored so that said dictionaries and said probability models are accessed during a renewed display of said at least portions of hypertext documents.

8. A hypertext navigation system controllable by spoken words, comprising:

means for recognizing spoken language to allocate a spoken word or a sequence of spoken words to entries of a dictionary or of a plurality of dictionaries;

a browser for opening a hypertext document potentially containing hypertext character sequences being potentially unknown words for hypertext navigation;

at least one first dictionary containing said hypertext character sequences of said hypertext document serving a purpose of hypertext navigation and containing phoneme sequences allocated to said hypertext character sequences as dictionary entries so that said hypertext navigation is carried out upon utterance of said phoneme sequences corresponding to said hypertext character sequences; and

at least one second dictionary that contains instructions of the hypertext navigation system as entries so that said instructions are carried out upon utterance of said instructions by a user.

9. A method for generating a hypertext document having a dictionary and a probability model, said dictionary containing hypertext character sequences of said hypertext document and phoneme sequences allocated to said hypertext character sequences as dictionary entries, and wherein said probability model makes it possible for said system for recognizing spoken language to allocate a spoken word or a sequence of spoken words to an entry of said dictionary from a traditional hypertext document, comprising the steps of:

investigating a source text of a traditional hypertext document for character sequences that serve a purpose of hypertext navigation, said character sequences including potentially unknown words,

extracting said character sequences from said source text to define a set of character sequences for said hypertext document;

allocating phoneme sequences to said character sequences of said set;

entering said character sequences of said set and appertaining phoneme sequences into a dictionary; and

producing a probability model for an acoustic voice recognition system for entries of said dictionary so as to effect activation of hypertext navigation in an interface program accessing the hypertext document upon utterance of said appertaining phoneme sequences.

10. A method as claimed in claim 9, further comprising the step of:

entering instructions of the hypertext navigation system together with phoneme sequences corresponding to said instructions into said dictionary in addition to said character sequences that serve the purpose of hypertext navigation.

11. A hypertext navigation system, comprising:

means for opening and displaying a computer document in a browser program;

means for identifying any hypertext elements in said computer document, said hypertext elements displaying at least one character sequence in said browser for each of said hypertext elements, said at least one character sequence being a potentially unknown word;

means for identifying a set of acceptable phoneme sequences corresponding to said displayed character sequences;

means for receiving spoken phoneme sequences from a user;

means for matching said spoken phoneme sequences of said user to said acceptable phoneme sequences of said set to identify a corresponding one of said hypertext elements;

means for activating a link of said corresponding one of said hypertext elements; and

means for opening a further computer document corresponding to said link activated by said means for activating.

12. A hypertext navigation system as claimed in claim 11, wherein said browser program has instructions of the hypertext navigation system, and further comprising:

means for matching said spoken phoneme sequences of said user to corresponding ones of said instructions; and

means for activating said corresponding ones of said instructions when a user utters said matching phoneme sequence.

13. A hypertext navigation system as claimed in claim 11, wherein said means for identifying any hypertext elements in said computer document investigates source text of said computer document.

14. A hypertext navigation system as claimed in claim 11, wherein said means for identifying a set of acceptable phoneme sequences corresponding to said displayed character sequences enter said acceptable phoneme sequences in a dictionary.

15. A hypertext navigation system as claimed in claim 11, wherein said means for matching said spoken phoneme sequences of said user to said acceptable phoneme sequences of said set includes a probability model.