Patents by Inventor Amarjit S. Bahl

Amarjit S. Bahl 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).

  • Method and system of enabling intelligent and lightweight speech to text transcription through distributed environment
    Patent number: 8438025
    Abstract: A system includes at least one wireless client device, a service manager, and a plurality of voice transcription servers. The service manager includes a resource management service and a profile management service. The client device communicates the presence of a voice transcription task to the resource management service. The resource management service surveys the plurality of voice transcription servers and selects one voice transcription server based on a set of predefined criteria. The resource management service then communicated an address of the selected server to the profile management service, which then transmits a trained voice profile or default profile to the selected server. The address of the selected server is then sent to the client device, which then transmits an audio stream to the server. Finally, the selected server transcribes the audio stream to a textual format.
    Type: Grant
    Filed: July 30, 2012
    Date of Patent: May 7, 2013
    Assignee: Nuance Communications, Inc.
    Inventors: Amarjit S. Bahl, Dalia Massoud, Dikran S. Meliksetian, Chen Shu, Michael Van Der Meulen, Nianjun Zhou
  • METHOD AND SYSTEM OF ENABLING INTELLIGENT AND LIGHTWEIGHT SPEECH TO TEXT TRANSCRIPTION THROUGH DISTRIBUTED ENVIRONMENT
    Publication number: 20120290301
    Abstract: A system includes at least one wireless client device, a service manager, and a plurality of voice transcription servers. The service manager includes a resource management service and a profile management service. The client device communicates the presence of a voice transcription task to the resource management service. The resource management service surveys the plurality of voice transcription servers and selects one voice transcription server based on a set of predefined criteria. The resource management service then communicated an address of the selected server to the profile management service, which then transmits a trained voice profile or default profile to the selected server. The address of the selected server is then sent to the client device, which then transmits an audio stream to the server. Finally, the selected server transcribes the audio stream to a textual format.
    Type: Application
    Filed: July 30, 2012
    Publication date: November 15, 2012
    Applicant: Nuance Communications, Inc.
    Inventors: Amarjit S. Bahl, Dalia Massoud, Dikran S. Meliksetian, Chen Shu, Michael Van Der Meulen, Nianjun Zhou
  • Method and system of enabling intelligent and lightweight speech to text transcription through distributed environment
    Patent number: 8311822
    Abstract: A system includes at least one wireless client device, a service manager, and a plurality of voice transcription servers. The service manager includes a resource management service and a profile management service. The client device communicates the presence of a voice transcription task to the resource management service. The resource management service surveys the plurality of voice transcription servers and selects one voice transcription server based on a set of predefined criteria. The resource management service then communicated an address of the selected server to the profile management service, which then transmits a trained voice profile or default profile to the selected server. The address of the selected server is then sent to the client device, which then transmits an audio stream to the server. Finally, the selected server transcribes the audio stream to a textual format.
    Type: Grant
    Filed: November 2, 2004
    Date of Patent: November 13, 2012
    Assignee: Nuance Communications, Inc.
    Inventors: Amarjit S. Bahl, Dalia Massoud, Dikran S. Meliksetian, Chen Shu, Michael Van Der Meulen, Nianjun Zhou
  • Method and system for creation of voice training profiles with multiple methods with uniform server mechanism using heterogeneous devices
    Patent number: 8239198
    Abstract: A system and method for creating user voice profiles enables a user to create a single user voice profile that is compatible with one or more voice servers. Such a system includes a training server that receives audio information from a client associated with a user and stores the audio information and corresponding textual information. The system further includes a training server adaptor. The training server adaptor is configured to receive a voice profile format and a communication protocol corresponding to one of the plurality of voice servers, convert the audio information and corresponding textual information into a format compatible with the voice profile format and communication protocol corresponding to the one of the plurality of voice servers, and provide the converted audio information and corresponding textual information to the one of the plurality of voice servers.
    Type: Grant
    Filed: October 20, 2008
    Date of Patent: August 7, 2012
    Assignee: Nuance Communications, Inc.
    Inventors: Nianjun Zhou, Amarjit S. Bahl, Michael Van Der Meulen
  • METHOD AND SYSTEM FOR CREATION OF VOICE TRAINING PROFILES WITH MULTIPLE METHODS WITH UNIFORM SERVER MECHANISM USING HETEROGENEOUS DEVICES
    Publication number: 20090043582
    Abstract: A system and method for creating user voice profiles enables a user to create a single user voice profile that is compatible with one or more voice servers. Such a system includes a training server that receives audio information from a client associated with a user and stores the audio information and corresponding textual information. The system further includes a training server adaptor. The training server adaptor is configured to receive a voice profile format and a communication protocol corresponding to one of the plurality of voice servers, convert the audio information and corresponding textual information into a format compatible with the voice profile format and communication protocol corresponding to the one of the plurality of voice servers, and provide the converted audio information and corresponding textual information to the one of the plurality of voice servers.
    Type: Application
    Filed: October 20, 2008
    Publication date: February 12, 2009
    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Nianjun Zhou, Amarjit S. Bahl, Michael Van Der Meulen
  • Method and system for creation of voice training profiles with multiple methods with uniform server mechanism using heterogeneous devices
    Patent number: 7440894
    Abstract: A system and method for creating user voice profiles enables a user to create a single user voice profile that is compatible with one or more voice servers. Such a system includes a training server that receives audio information from a client associated with a user and stores the audio information and corresponding textual information. The system further includes a training server adaptor. The training server adaptor is configured to receive a voice profile format and a communication protocol corresponding to one of the plurality of voice servers, convert the audio information and corresponding textual information into a format compatible with the voice profile format and communication protocol corresponding to the one of the plurality of voice servers, and provide the converted audio information and corresponding textual information to the one of the plurality of voice servers.
    Type: Grant
    Filed: August 9, 2005
    Date of Patent: October 21, 2008
    Assignee: International Business Machines Corporation
    Inventors: Nianjun Zhou, Amarjit S. Bahl, Michael Van Der Meulen