Speech recognition control of remotely controllable devices in a home network environment

• US 6,535,854 B2
• Filed: 10/19/1998
• Issued: 03/18/2003
• Est. Priority Date: 10/23/1997
• Status: Expired due to Term

• Current Assignee: Sony International Europe Gmbh (Sony Group Corp.)
• Original Assignee: Sony International Europe Gmbh (Sony Group Corp.)
• Inventors: Rapp, Stefan, Goronzy, Silke, Buchner, Peter, Kompe, Ralf
• Primary Examiner(s): Banks-Harold, Marsha D.
• Assistant Examiner(s): Storm, Donald L.
• Application Number:
  US09/175,382
• Publication Number:
  US 20020069063A1
• Time in Patent Office: 1,611 Days
• Field of Search: 704/275, 704/270, 704/200, 704/231, 340/825.07, 340/825.25, 700/94, 379/102.03
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 12/2803 Home automation networks
• CPC Class Codes: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: H04L 12/40117 Interconnection of audio or video/imaging devices home automation networks H04L12/2803; bitstream network arrangements specially adapted for distribution of digital video signals H04N7/24

Abstract

Home networks low-cost digital interfaces are introduced that integrate entertainment, communication and computing electronics into consumer multimedia. Normally, these are low-cost, easy to use systems, since they allow the user to remove or add any kind of network devices with the bus being active. To improve the user interface a speech unit (2) is proposed that enables all devices (11) connected to the bus system (31) to be controlled by a single speech recognition device. The properties of this device, e.g. the vocabulary can be dynamically and actively extended by the consumer devices (11) connected to the bus system (31). The proposed technology is independent from a specific bus standard, e.g. the IEEE 1394 standard, and is well-suited for all kinds of wired wireless home networks. The speech unit (2) receives data and messages from the device. The speech unit (2) recognizes speaker-dependent commands. A Speech synthesizer synthesizes messages. A remotely controllable device (11) has access to a medium which may be a CD-ROM. The device may ask for a logical name or identifier.

Claims

1. Speech unit for generating user-network-commands according to electric signals provided by a microphone to control a remotely controllable device connected to said speech unit, characterized by;

a control unit in said speech unit to send control-network-commands to said device connected to said speech unit so that said device transmits device or medium dependent vocabulary and/or grammars and corresponding user-network-commands to said speech unit and to receive data and messages from said device; and

a memory to store said device or medium dependent vocabulary and/or grammars and corresponding user-network-commands transmitted by said remotely controllable device connected to said speech unit,

said speech unit generates and stores in said memory, new user-network-commands and corresponding vocabulary to control said remotely controllable device based on a dialogue between said speech unit and a user.

2. Speech unit according to claim 1, characterized by an interface connected to a network system to which a remotely controllable device can be connected that can be controlled via said network system, to send generated user-network-commands and control-network-commands via said network system to said remotely controllable device and to receive data and messages from said remotely controllable device.

3. Speech unit according to claim 2, characterized in that said control unit determines what kind of devices are connected to a network system, to send said control-network-commands to said devices, and to receive data from said devices.

4. Speech unit according to claim 1, characterized in that said device is wired or wireless connected to said, speech unit.

5. Speech unit according claim 1, characterized by a memory to initially store general vocabulary and grammars based on which general user-network-commands are generated.

6. Speech unit according to claim 1, characterized by a speaker recognition section to identify different users according to said electric signals provided by said microphone to be able to generate speaker dependent user-network-commands.

7. Speech unit according to claim 1, characterized by a speech synthesizer to synthesize messages from said device and from said speech unit itself and to output them to a user via a loudspeaker.

8. Speech unit according to claim 1, characterized by a microphone and/or a loudspeaker.

9. Speech unit according to claim 1, characterized in that said microphone and/or a loudspeaker are/is remotely connected to said speech unit either wired or wireless either direct or via a network.

10. Speech unit for generating user-network-commands according to electric signals provided by a microphone to control a remotely controllable device characterized by an interface connected to a network system to which said remotely controllable device is connected that can be controlled via said network system, to send generated user-network-commands via said network system to said remotely controllable device and to receive data and message from said remotely controllable device, said user-network-commands are requested by control-network-commands from a control unit in said speech unit, said speech unit generates and stores in a memory, new user-network-commands and corresponding vocabulary to control said remotely controllable device based on a dialogue between said speech unit and a user.

11. Speech unit according to claim 10, characterized in that said interface is connected to said network system via a public telephone network.

12. Speech unit according to claim 10, characterized in that said interface is connected to said network system via another network system.

13. Remotely controllable device, comprising:

a first control unit to extract user-network-commands directed to said device and to control the functionality of said remotely controllable device according to said extracted user-network-commands, characterized in that said first control unit also extracts control-network-commands directed to said remotely controllable device, said control-network-commands are sent by a second control unit in a speech unit, and, according to said extracted control-network-commands, controls the transmission of device dependent user-network-commands and corresponding vocabulary and/or grammars stored in a memory of said remotely controllable device useable by said speech unit connected thereto to convert spoken-commands from a user into user-network-commands to control the functionality of said remotely controllable device, said speech unit generates and stores in said memory, new user-network-commands and corresponding vocabulary to control said remotely controllable device based on a dialogue between said speech unit and said user.

14. Remotely controllable device according to claim 13, characterized by an interface connected to a network system to which said device and said speech unit can be connected to receive and transmit commands, data and messages.

15. Remotely controllable device, comprising:

a first control unit also extracts control-network-commands directed to said device and to control the functionality of said remotely controllable device according to said extracted user-network-commands, characterized in that said first control unit also extracts control-network-commands directed to said remotely controllable device, said control-network-commands are sent by a second control unit in a speech unit, and, according to said extracted control-network-commands, controls the transmission of medium dependent user-network-commands and corresponding vocabulary and/or grammars stored on a medium accessable by said remotely controllable device useable by said speech unit connected thereto to convert spoken-commands from a user into a user-network-commands to control the functionality of said remotely controllable device in regard to said accessable medium or to control the functionality of said or another remotely controlled device, said speech unit generates and stores in a memory, new user-network-commands and corresponding vocabulary to control said remotely controllable device based on a dialogue between said speech unit and said user.

16. Remotely controllable device according to claim 15, characterized in that said medium accessable by said remotely controllable device is a compact disc.

17. Remotely controllable device according to claim 15, characterized in that said medium accessable by said remotely controllable device is an internet page or information page transmitted via digital broadcasting.

18. Method of self-initialization of a speech unit connected to a remotely controllable device, comprising the following steps:

a) send a control-network-command from a control unit in said speech unit to said remotely controllable device to control said device to transmit device or medium dependent user-network-commands to control said device and the corresponding vocabulary and/or grammars;

b) receive said device or medium dependent user-network-commands and the corresponding vocabulary and/or grammars from said device;

c) update vocabulary and/or grammars and the corresponding user-network-commands in a memory; and

d) generate and store in said memory new vocabulary and/or grammars and corresponding user-network-commands based on a dialogue between said speech unit and a user.

19. Method according to claim 18, charaterized by the following steps:

ask for a logical name or identifier of said device offering the device dependent user-network-commands and the corresponding vocabulary and/or grammars;

receive logical name or identifier; and

assign vocabulary and grammars and corresponding user-network-commands for said device to the received logical name or identifier when said vocabulary and/or grammars and the corresponding user-network-commands are updated in said memory in order to create device dependent user-network-commands.

20. Method according to claim 19, characterized in that said logical name of said device is either determined by a user or by said device itself.

21. Method according to claim 19, characterized in that said identifier includes address and name of said device.

22. Method according to claim 18, characterized by the following steps:

send a control-network-command to identify a user dependent mapping for the vocabulary and/or grammars and corresponding user-network-commands;

receiving at least one of a name, an identifier, and a speech sample of a user that the dependency should be created for; and

assign the vocabulary and/or grammars and corresponding user-network-commands for said device to a received name or names, an identifier or identifiers or speech sample of said user when said vocabulary and/or grammars and the corresponding user-network-commands are updated in said memory in order to create user dependent user-network-commands.