US 8,032,383 B1Granted

Speech controlled services and devices using internet

AssigneeFoneWeb, Inc.

InventorsVinod K. Bhardwaj, Scott England, Dean Whitlock

Life of this patent

Estimating the term…

Loading patent…

Abstract

A speech service, including a speech-to-text engine and a text-to-speech engine, creates and maintains user profiles at a central location accessible over the Internet. A user connects to a software application over a mobile telephone and delivers a voice command. The speech service transcribes the voice command into a text command for the software application. The software application performs a service desired by the user and delivers a text result to the speech service that is converted into a speech result that is delivered to the user. A user speaks to a hardware device to perform a function. The hardware device sends the speech to the speech service over the Internet that transcribes the speech into a text command that is sent over the Internet to a device service provider. The device service provider maps the text command into a device command that is then sent back over the Internet to the hardware device to perform the function. A remote hardware device can be controlled using the software application.

Claims20

Dependent claims

A method of controlling a hardware device comprising:

receiving a voice command and a device identifier over a network from a remote hardware device, said voice command originating with a user, wherein said voice command requests a function be performed by said hardware device that is desired by said user, and wherein said device identifier identifies said hardware device;
identifying a user speech profile using said device identifier, wherein said user speech profile is a device profile that represents a plurality of users that speak to said remote hardware device, the vocabulary of said device profile being built up using the speech input of said plurality of users;
retrieving said identified user speech profile from a central database;
converting said voice command to a corresponding text command using a speech-to-text engine and said user speech profile;
delivering said text command to a device service provider;
mapping said text command into a corresponding device command by said device service provider, said device command being executable by said hardware device;
and
delivering said device command over said network to said remote hardware device in order that said hardware device perform said function requested by said user.

5 more elements

A method of controlling a hardware device comprising:

receiving a voice command and a device identifier over a network from a device service provider, said voice command originating with a user and said device identifier originating with an identifying a hardware device, wherein said voice command requests a function be performed by said hardware device that is desired by said user;
identifying a user speech profile using said device identifier, wherein said user speech profile is a device profile that represents a plurality of users that speak to said remote hardware device, the vocabulary of said device profile being built up using the speech input of said plurality of users;
retrieving said identified user speech profile from a central database;
converting said voice command to a corresponding text command using a speech-to-text engine and said user speech profile;
delivering said text command to said device service provider;
mapping said text command into a corresponding device command by said device service provider, said device command being executable by said hardware device;
and
delivering said device command over said network to said remote hardware device in order that said hardware device perform said function requested by said user.

5 more elements

Dependencies are inferred from the claim text.

Facts

Application: 11/763,870Filed 15 Jun 2007 · us provisional application
Priority: 4 May 2007
Granted: 4 Oct 2011
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G10L 15/30
Constructional details of speech recognition systems: distributed recognition, e.g. in client-server systems, for mobile phones or network…
G10L 2015/223
Procedures used during a speech recognition process, e.g. man-machine dialogue: execution procedure of a spoken command
G10L 2015/228
Using non-speech characteristics: of application context
G10L
Speech analysis techniques or speech synthesis