Patents by Inventor Min Ke
Min Ke has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 9263039Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: GrantFiled: September 29, 2014Date of Patent: February 16, 2016Assignee: Nuance Communications, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Publication number: 20150019217Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: ApplicationFiled: September 29, 2014Publication date: January 15, 2015Inventors: Philippe DI CRISTO, Min KE, Robert A. KENNEWICK, Lynn Elise ARMSTRONG
-
Patent number: 8849670Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: GrantFiled: November 30, 2012Date of Patent: September 30, 2014Assignee: VoiceBox Technologies CorporationInventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Publication number: 20130297293Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: ApplicationFiled: November 30, 2012Publication date: November 7, 2013Applicant: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Patent number: 8326634Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: GrantFiled: February 2, 2011Date of Patent: December 4, 2012Assignee: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Patent number: 8150694Abstract: The system and method described herein may provide an acoustic grammar to dynamically sharpen speech interpretation. In particular, the acoustic grammar may be used to map one or more phonemes identified in a user verbalization to one or more syllables or words, wherein the acoustic grammar may have one or more linking elements to reduce a search space associated with mapping the phonemes to the syllables or words. As such, the acoustic grammar may be used to generate one or more preliminary interpretations associated with the verbalization, wherein one or more post-processing techniques may then be used to sharpen accuracy associated with the preliminary interpretations. For example, a heuristic model may assign weights to the preliminary interpretations based on context, user profiles, or other knowledge and a probable interpretation may be identified based on confidence scores associated with one or more candidate interpretations generated with the heuristic model.Type: GrantFiled: June 1, 2011Date of Patent: April 3, 2012Assignee: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Patent number: 8069046Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: GrantFiled: October 29, 2009Date of Patent: November 29, 2011Assignee: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Publication number: 20110231188Abstract: The system and method described herein may provide an acoustic grammar to dynamically sharpen speech interpretation. In particular, the acoustic grammar may be used to map one or more phonemes identified in a user verbalization to one or more syllables or words, wherein the acoustic grammar may have one or more linking elements to reduce a search space associated with mapping the phonemes to the syllables or words. As such, the acoustic grammar may be used to generate one or more preliminary interpretations associated with the verbalization, wherein one or more post-processing techniques may then be used to sharpen accuracy associated with the preliminary interpretations. For example, a heuristic model may assign weights to the preliminary interpretations based on context, user profiles, or other knowledge and a probable interpretation may be identified based on confidence scores associated with one or more candidate interpretations generated with the heuristic model.Type: ApplicationFiled: June 1, 2011Publication date: September 22, 2011Applicant: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Patent number: 7983917Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: GrantFiled: October 29, 2009Date of Patent: July 19, 2011Assignee: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Publication number: 20110131045Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: ApplicationFiled: February 2, 2011Publication date: June 2, 2011Applicant: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Patent number: 7917367Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: GrantFiled: November 12, 2009Date of Patent: March 29, 2011Assignee: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Publication number: 20100057443Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: ApplicationFiled: November 12, 2009Publication date: March 4, 2010Applicant: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Publication number: 20100049514Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: ApplicationFiled: October 29, 2009Publication date: February 25, 2010Applicant: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Publication number: 20100049501Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: ApplicationFiled: October 29, 2009Publication date: February 25, 2010Applicant: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Patent number: 7640160Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: GrantFiled: August 5, 2005Date of Patent: December 29, 2009Assignee: VoiceBox Technologies, Inc.Inventors: Philippe Di Cristo, Min Ke, Robert A. Kennewick, Lynn Elise Armstrong
-
Patent number: 7634409Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: GrantFiled: August 31, 2006Date of Patent: December 15, 2009Assignee: VoiceBox Technologies, Inc.Inventors: Robert A. Kennewick, Min Ke, Michael Tjalve, Philippe Di Cristo
-
Patent number: 7321523Abstract: A monitoring system capable of monitoring utilization of a processing device in a computer. The monitoring system includes a power supply voltage for supplying a core voltage to the processing device, and a comparator for comparing a voltage proportional to the core voltage to a reference voltage and producing a sense voltage. The resulting sense voltage is used to control a processing device management process, or alternatively may be used to control a variety of other processes including cooling fan operation.Type: GrantFiled: December 30, 2004Date of Patent: January 22, 2008Assignee: ASUSTeK Computer Inc.Inventor: Jia-Min Ke
-
Publication number: 20070186333Abstract: A deodorizing system includes a first main conduit, a suction generating device, a first terminal conduit, a first odor generating source, a second terminal conduit, a second odor generating source and a first adjusting damper. The suction generating device is disposed in the downstream of the first main conduit. The first terminal conduit is connected to the first main conduit by a first junction. The first odor generating source is connected to the first terminal conduit. The second terminal conduit is connected to the first main conduit by a second junction. The second odor generating source is connected to the second terminal conduit. The first adjusting damper is positioned in the first main conduit between the first junction and the second junction for regulating the airflow ratio of the first odor generating source to the second odor generating source.Type: ApplicationFiled: December 17, 2004Publication date: August 16, 2007Inventors: Huei-Min Ke, Liang-Yi Ke
-
Publication number: 20070055525Abstract: An enhanced system for speech interpretation is provided. The system may include receiving a user verbalization and generating one or more preliminary interpretations of the verbalization by identifying one or more phonemes in the verbalization. An acoustic grammar may be used to map the phonemes to syllables or words, and the acoustic grammar may include one or more linking elements to reduce a search space associated with the grammar. The preliminary interpretations may be subject to various post-processing techniques to sharpen accuracy of the preliminary interpretation. A heuristic model may assign weights to various parameters based on a context, a user profile, or other domain knowledge. A probable interpretation may be identified based on a confidence score for each of a set of candidate interpretations generated by the heuristic model. The model may be augmented or updated based on various information associated with the interpretation of the verbalization.Type: ApplicationFiled: August 31, 2006Publication date: March 8, 2007Inventors: Robert Kennewick, Min Ke, Michael Tjalve, Philippe Cristo
-
Publication number: 20070033005Abstract: Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural enviromnent for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.Type: ApplicationFiled: August 5, 2005Publication date: February 8, 2007Applicant: VoiceBox Technologies, Inc.Inventors: Philippe Cristo, Min Ke, Robert Kennewick