Speech recognition method for activating a hyperlink of an internet page

• US 6,604,076 B1
• Filed: 11/09/2000
• Issued: 08/05/2003
• Est. Priority Date: 11/09/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications Austria Gmbh (Microsoft Corporation)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Kubesch, Dieter, Holley, Martin
• Primary Examiner(s): To, Doris H.
• Assistant Examiner(s): Nolan, Daniel A.
• Application Number:
  US09/709,261
• Time in Patent Office: 999 Days
• Field of Search: 704/270, 704/270.1, 704/275, 704/235, 704/231
• US Class Current: 704/270.1
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A speech recognition method is disclosed for activating a hyperlink of an Internet page. In particular the method comprises determining hypertexts of the hyperlinks in text information, determining corresponding first phoneme sequences of hypertexts, receiving a spoken command from a user, determining a second phoneme sequence corresponding to the spoken command, determining the hyperlink selected by the user using the first and second phoneme sequences, activating the selected hyperlink, where one quality value is determined for each hypertext when first phoneme sequences are determined and where an extra hypertext is determined when the quality value of a hypertext is below a threshold and is assigned to the hypertext of the Internet page or in lieu of the hypertext, and where a first phoneme sequence determined for the extra hypertext has a quality value that exceeds the threshold.

Claims

1. A speech recognition method for activating a hyperlink of text information of an Internet page displayed to a user, the method comprising the following steps:

determining hypertexts of the hyperlinks in the text information shown and determining corresponding first phoneme sequences of these hypertexts and

receiving a spoken command from a user which represents at least part of a determined hypertext, and

determining a second phoneme sequence corresponding to the spoken command and

determining the hyperlink selected by the user by comparison of the determined second phoneme sequence with determined first phoneme sequences and

activating the selected hyperlink,

wherein one quality value is determined for each hypertext when first phoneme sequences corresponding to the hypertexts is determined and in that

an extra hypertext is determined when the quality value of a hypertext is below a quality threshold and is assigned to the hypertext in the text information of the Internet page or in lieu of the hypertext, while a first phoneme sequence determined for the extra hypertext has a quality value that exceeds the quality threshold.

2. The speech recognition method as claimed in claim 1, wherein the extra hypertext is formed by a number.

3. The speech recognition method as claimed in claim 2, wherein when the numerical value of the number is laid down, all the hypertexts represented above determined in the text information of the Internet page and assigned to the extra hypertext in the text information of the Internet page are taken into account.

7. A computer program product which can be loaded directly into the internal memory of a digital computer and contains software code sections, wherein the steps of the method as claimed in claim 1 are made with a computer when the product runs on the computer.

8. The computer program product as claimed in claim 7, wherein the computer program is stored on a medium that can be read by the computer.

4. A speech recognition device for controlling an Internet browser, which browser is arranged for receiving text information containing a hyperlink of an Internet page, comprising:

hyperlink identification means for determining hypertexts of the hyperlinkin the text information of the received Internet page and

correlation means for determining corresponding first phoneme sequences based on these hypertexts and

receiving means for receiving a spoken command from a user, which represents at least part of a determined hypertext, and

speech recognition means for determining a second phoneme sequence corresponding to the spoken command and

command word determining means for determining the hyperlink selected by the user by comparison of the determined second phoneme sequence with determined first phoneme sequences and

control means for controlling the Internet browser to enable reception of the text information of the Internet page featured by the selected hyperlink, wherein the correlation means are arranged for determining one quality value per hypertext when the first phoneme sequences corresponding to the hypertexts are determined and in that

the correlation means, when the quality value of a hypertext is below a quality threshold, is arranged for determining an extra hypertext for this hypertext, while the extra hypertext assigned to this hypertext or replacing this hypertext in the text information of the Internet page can be represented and one of the correlation means for the first phoneme sequence determined for the extra hypertext has a quality value that exceeds the quality threshold.

5. The speech recognition device as claimed in claim 4, wherein the correlation means are arranged for determining a number as extra hypertext.

6. The speech recognition device as claimed in claim 5, wherein, when the numerical value of the number is determined, the correlation means are arranged for taking all the hypertexts standing before the extra hypertext in the text information of the Internet page determined in the text information of the Internet page into account.