Automatic recognition of audio information in a broadcast program

• US 6,011,854 A
• Filed: 09/18/1997
• Issued: 01/04/2000
• Est. Priority Date: 09/18/1997
• Status: Expired due to Term

• Current Assignee: Sony Corporation (Sony Group Corp.), Sony Electronics Inc. (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.), Sony Electronics Inc. (Sony Group Corp.)
• Inventors: Van Ryzin, John M.
• Primary Examiner(s): Lee, Ping
• Application Number:
  US08/932,494
• Time in Patent Office: 838 Days
• Field of Search: 381/77, 381/86, 381/2, 455/45, 455/186.1, 455/161.1, 455/161.2
• US Class Current: 381/77
• CPC Class Codes: G08G 1/093 Data selection, e.g. prioritizing information, managing message queues, selecting the information to be output
• CPC Class Codes: H03J 2200/20 Radio receiver with possibility to choose a station with a certain program style

Abstract

An audio processing system searches for information reports or updates (such as traffic, weather, time, sports, news, and the like) broadcast over one or several radio stations. The search is based on at least one keyword (such as "traffic", "weather", "time", "sports", "news" depending on the desired report) being preselected by the user, and being entered into the audio processing system. While speech recognition software used by the audio processing system scans the radio station for the requested information report, the user may listen to other audio sources (a CD, a tape, another radio station broadcast, etc.) without being required to monitor (that is, listen to) the information content from those audio sources. Once the requested information report is detected based on the entered keyword used in the radio broadcast, the audio processing system switches its audio output to the radio station transmitting the desired broadcast, such that the user can timely and conveniently listen to the traffic, weather, time, sports, and/or news reports or updates.

Claims

1. Audio processing apparatus for outputting preselected audio information detected from a program which is reproduced via output means, said audio processing apparatus comprising:

a tuner for tuning to an arbitrary broadcast station and for generating an audio output signal corresponding to said program transmitted by said arbitrary broadcast station;

a programmable controller for receiving said audio output signal from said tuner and for receiving from a user an arbitrary keyword representative of said preselected audio information, said programmable controller determining whether said preselected audio information is present in said audio output signal based on the received arbitrary keyword by executing a speech recognition operation for recognizing the received arbitrary keyword in the transmitted program; and

a switch controlled by said programmable controller for supplying said audio output signal to said output means for reproducing said program when said preselected audio information is present in said audio output signal.

2. The apparatus according to claim 1, further comprising at least one device for generating audio data reproduced via said output means, said one device being connected to said switch for selectively providing said generated audio data to said output means when said preselected audio information is not present in said audio output signal.

3. The apparatus according to claim 1, wherein said programmable controller is operative to control said tuner for sequentially tuning to a plurality of broadcast stations with a predetermined time interval between tuning to a next broadcast station.

4. The apparatus according to claim 1, wherein said programmable controller is operative to control said tuner for tuning to said broadcast station at a predetermined time.

5. An audio processing method for outputting preselected audio information detected from a program which is reproduced via output means, said method comprising the steps of:

tuning to an arbitrary broadcast station for generating an audio output signal corresponding to said program transmitted by said arbitrary broadcast station;

receiving from a user an arbitrary keyword representative of said preselected audio information;

determining whether said preselected audio information is present in said audio output signal based on the received arbitrary keyword by executing a speech recognition operation for recognizing the received arbitrary keyword in the transmitted program; and

supplying said audio output signal to said output means for reproducing said program when said preselected audio information is present in said audio output signal.

6. The method according to claim 5, further comprising generating audio data which is selectively provided to said output means when said preselected audio information is not present in said audio output signal.

7. The method according to claim 5, wherein said step of tuning comprises sequentially tuning to a plurality of broadcast stations with a predetermined time interval between tuning to a next broadcast station.

8. The method according to claim 5, wherein said step of tuning comprises tuning to said broadcast station at a predetermined time.