Methods and apparatus for generating, updating and distributing speech recognition models
Techniques for generating, distributing, and using speech recognition models are described. A shared speech processing facility is used to support speech recognition for a wide variety of devices with limited capabilities including business computer systems, personal data assistants, etc., which are coupled to the speech processing facility via a communications channel, e.g., the Internet. Devices with audio capture capability record and transmit to the speech processing facility, via the Internet, digitized speech and receive speech processing services, e.g., speech recognition model generation and/or speech recognition services, in response. The Internet is used to return speech recognition models and/or information identifying recognized words or phrases. Thus, the speech processing facility can be used to provide speech recognition capabilities to devices without such capabilities and/or to augment a device's speech processing capability. Voice dialing, telephone control and/or other services are provided by the speech processing facility in response to speech recognition results.
1 - 20 . (canceled).
21 . A speech processing method, the method comprising the steps of:
receiving speech from a remote device over the Internet via an E-mail message which includes said speech as a file attached to said message;
processing the speech to generate a speech recognition model there from; and
transmitting the generated speech recognition model to the remote device.
22 . The method of claim 21 , wherein said speech is a digital speech signal, the method further comprising the steps of:
storing the received digital speech signal in a training database including other speech samples corresponding to the same word.
23 . The method of claim 21 , wherein said message includes model type information, and wherein the step of processing the speech to generate a speech recognition model includes performing a speech recognition model training operation to train a model of the type indicated by the model type information.
24 . The method of claim 21 , further comprising the step of:
receiving an existing speech recognition model; and
wherein the step of processing the speech to generate a speech recognition model there from includes:
performing a model training operation using said speech and speech characteristic information obtained from the existing speech recognition model.
25 . The method of claim 24 , wherein the generated speech recognition model includes at least one type of speech characteristic information that was not included in the received existing speech recognition model.
26 . The method of claim 25 , wherein the at least one type of speech characteristic information includes one of change in energy information and change in amplitude information.
27 . The method of claim 24 , wherein the step of transmitting the generated speech recognition model to the remote device includes:
transmitting the generated speech recognition model over the Internet as part of an E-mail message directed to the remote device.
28 . The method of claim 21 , further comprising the steps of:
storing the generated speech recognition model in a model training database; and
periodically transmitting models in the model training database to a plurality of speech recognition systems.
29 . The method of claim 28 , wherein the step of periodically transmitting models includes;
transmitting the models over the Internet.
30 - 36 . (canceled).