US 7,689,415 B1Granted

Real-time speech recognition over the internet

AssigneeGlobalEnglish Corporation

InventorChristopher S. Jochumson

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods and systems for handling speech recognition processing in effectively real-time, via the Internet, in order that users do not experience noticeable delays from the start of an exercise until they receive responsive feedback. A user uses a client to access the Internet and a server supporting speech recognition processing, e.g., for language learning activities. The user inputs speech to the client, which transmits the user speech to the server in approximate real-time. The server evaluates the user speech in context of the current speech recognition exercise being executed, and provides responsive feedback to the client, again, in approximate real-time, with minimum latency delays. The client upon receiving responsive feedback from the server, displays, or otherwise provides, the feedback to the user.

Claims19

Dependent claims

A system supporting speech recognition comprising:

two or more clients, each client comprising the capability to receive audio speech from a user, store the audio speech in one or more buffers, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit a packet of encoded audio speech over the Internet before all of the audio speech is received;
and
a server, the server comprising the capability to receive packets of encoded audio speech from at least two clients, decode each of the packets of audio speech and store the resultant raw speech into one or more buffers for the respective client, and evaluate the resultant raw speech received from each of the at least two clients,
wherein the server further comprises the capability to transmit a response to a client, the response a result of the server's evaluation of the resultant raw speech received from the client,
a client of the two or more clients further comprises the capability to receive the response from the server,
the response is in text format, and a client of the two or more clients comprises a text-to-speech engine which converts the text format response to audio data, and an audio output device that the client uses to output the audio data to a user, and
a level of processing used in the evaluation of the resultant raw speech received from a client is alterable based on a parameter communicated between the client and the server.

4 more elements

A system supporting speech recognition comprising:

two or more clients, each client comprising the capability to receive audio speech from a user, store the audio speech in one or more buffers, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit a packet of encoded audio speech over the Internet before all of the audio speech is received;
and
a server, the server comprising the capability to receive packets of encoded audio speech from at least two clients, decode each of the packets of audio speech and store the resultant raw speech into one or more buffers for the respective client, and evaluate the resultant raw speech received from each of the at least two clients,
wherein the server further comprises the capability to transmit a response to a client, the response a result of the server's evaluation of the resultant raw speech received from the client,
a client of the two or more clients further comprises the capability to receive the response from the server,
the response is in text format, and a client of the two or more clients comprises a text-to-speech engine which converts the text format response to audio data, and an audio output device that the client uses to output the audio data to a user, and
a processing time used to evaluate the resultant raw speech will vary based on a value communicated to the server from a client.

4 more elements

A system supporting speech recognition comprising:

two or more clients, each client comprising the capability to receive audio speech from a user, store the audio speech in one or more buffers, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit a packet of encoded audio speech over the Internet before all of the audio speech is received;
and
a server, the server comprising the capability to receive packets of encoded audio speech from at least two clients, decode each of the packets of audio speech and store the resultant raw speech into one or more buffers for the respective client, and evaluate the resultant raw speech received from each of the at least two clients,
wherein the server further comprises two or more stored text format files, and the server selects a stored text format file to transmit to a client of the two or more clients as a result of the server's evaluation of the resultant raw speech received from the client,
the server further comprises the capability to partition a stored text format file into two or more packets for the transmission over the Internet, and to transmit each packet over the Internet to a client,
a client further comprises an audio output device, and the capability to receive the packets of text format, convert the packets of text format to audio data and play the audio data to a user, and
a level of processing used in the evaluation of the resultant raw speech received from a client is alterable based on a parameter communicated between the client and the server.

4 more elements

A system supporting speech recognition comprising:

two or more clients, each client comprising the capability to receive audio speech from a user, store the audio speech in one or more buffers, each buffer comprising a portion of the received audio speech, encode a buffer of the received audio speech before all of the audio speech is received, package the encoded buffer to receive audio speech into one or more packets to be transmitted over the Internet before all of the audio speech is received, and transmit a packet of encoded audio speech over the Internet before all of the audio speech is received;
and
a server, the server comprising the capability to receive packets of encoded audio speech from at least two clients, decode each of the packets of audio speech and store the resultant raw speech into one or more buffers for the respective client, and evaluate the resultant raw speech received from each of the at least two clients,
wherein the server further comprises two or more stored text format files, and the server selects a stored text format file to transmit to a client of the two or more clients as a result of the server's evaluation of the resultant raw speech received from the client,
the server further comprises the capability to partition a stored text format file into two or more packets for the transmission over the Internet, and to transmit each packet over the Internet to a client,
a client further comprises an audio output device, and the capability to receive the packets of text format, convert the packets of text format to audio data and play the audio data to a user, and
a processing time used to evaluate the resultant raw speech will vary based on a value communicated to the server from a client.

4 more elements

Dependencies are inferred from the claim text.

Facts

Application: 11/925,558Filed 26 Oct 2007 · division
Priority: 4 Oct 1999
Granted: 30 Mar 2010
Term ends: Not estimatedThe source records don’t support an estimate.

Classification7 codes

G10L 15/30
Constructional details of speech recognition systems: distributed recognition, e.g. in client-server systems, for mobile phones or network…
G10L 13/08
Speech synthesis; Text to speech systems: text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme…
G10L 15/00
Speech recognition
G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue

Family

Application09/412,043Parent of this continuation · filed 4 Oct 1999
Application10/199,395Parent of this continuation · filed 19 Jul 2002
US 6,453,290 B1Parent of this continuation · filed 17 Sep 2002
Application10/711,114Parent of this division · filed 24 Aug 2004
US 6,865,536 B2Parent of this continuation · filed 8 Mar 2005
US 7,330,815 B1Parent of this division
Application10/711,114Parent of this continuation
US 2003/0046065 A1Published application
US 7,689,415 B1This patent

From the US filing history. Foreign family members aren’t listed.