Configuring a speech engine for a multimodal application based on location

1. A method of configuring a speech engine for a multimodal application based on location, the multimodal application operating on a multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to a speech engine, the method comprising:

receiving a location change notification in a location change monitor from a device location manager, the device location manager operatively coupled to a position detection component of the multimodal device, the location change notification specifying a current location of the multimodal device;

identifying in a configuration parameter repository, location-based configuration parameters for the speech engine in dependence upon the current location of the multimodal device, the location-based configuration parameters specifying a configuration for the speech engine at the current location, wherein the location-based configuration parameters include an identifier for an acoustic model from among a plurality of acoustic models including a first acoustic model and a second acoustic model, an identifier for a lexicon from among a plurality of lexicons including a first lexicon and a second lexicon, speech transition times, silence detection times, speech timeouts, gain maps, and a configuration for use by a text-to-speech (‘TTS’) engine including a voice used in synthesizing speech from text, wherein each of the first acoustic model and the second acoustic model associates acoustic features with phonemes, wherein the first lexicon and the second lexicon specify a different phoneme representation for a same word; and

updating, by the location change monitor, a current configuration for the speech engine according to the identified location-based configuration parameters.

2. The method of claim 1 further comprising:

receiving a position notification in the device location manager for the multimodal device from a position detection module, the position detection module operatively coupled to the position detection component of the multimodal device, the position notification specifying a geographic coordinate for the multimodal device; and

determining, by the device location manager, the current location of the multimodal device in dependence upon the geographic coordinate.

3. The method of claim 1 , wherein the first acoustic model and the second acoustic model associate different audio input with a same phoneme.

4. The method of claim 1 , wherein the location change notification includes a timestamp specifying a time at which the multimodal device arrived at the current location, and wherein identifying the location-based configuration parameters in the configuration parameter repository comprises identifying the location-based configuration parameters based, at least in part, on the timestamp specified in the location change notification and at least one previous timestamp included in a previous location change notification.

5. An apparatus for configuring a speech engine for a multimodal application based on location, the multimodal application operating on a multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to a speech engine, the apparatus comprising a computer processor and a computer memory operatively coupled to the computer processor, the computer memory having disposed within it computer program instructions that, when executed by the computer processor, perform a method of:

receiving a location change notification in a location change monitor from a device location manager, the device location manager operatively coupled to a position detection component of the multimodal device, the location change notification specifying a current location of the multimodal device;

identifying in a configuration parameter repository, location-based configuration parameters for the speech engine in dependence upon the current location of the multimodal device, the location-based configuration parameters specifying a configuration for the speech engine at the current location, wherein the location-based configuration include an identifier for an acoustic model from among a plurality of acoustic models including a first acoustic model and a second acoustic model, an identifier for a lexicon from among a plurality of lexicons including a first lexicon and a second lexicon, speech transition times, silence detection times, speech timeouts, gain maps, and a configuration for use by a text-to-speech (‘TTS’) engine including a voice used in synthesizing speech from text, wherein each of the first acoustic model and the second acoustic model associates acoustic features with phonemes, wherein the first lexicon and the second lexicon specify a different phoneme representation for a same word; and

updating, by the location change monitor, a current configuration for the speech engine according to the identified location-based configuration parameters.

6. The apparatus of claim 5 further comprising:

receiving a position notification in the device location manager for the multimodal device from a position detection module, the position detection module operatively coupled to the position detection component of the multimodal device, the position notification specifying a geographic coordinate for the multimodal device; and

determining, by the device location manager, the current location of the multimodal device in dependence upon the geographic coordinate.

7. The apparatus of claim 5 , wherein the first acoustic model and the second acoustic model associate different audio input with a same phoneme.

8. The apparatus of claim 5 , wherein the location change notification includes a timestamp specifying a time at which the multimodal device arrived at the current location, and wherein identifying the location-based configuration parameters in the configuration parameter repository comprises identifying the location-based configuration parameters based, at least in part, on the timestamp specified in the location change notification and at least one previous timestamp included in a previous location change notification.

9. A non-transitory computer readable recordable medium encoded with a plurality of instructions that, when executed on a computer, perform a method of configuring a speech engine for a multimodal application based on location, the multimodal application operating on a multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes, the multimodal application operatively coupled to a speech engine, the method comprising:

receiving a location change notification in a location change monitor from a device location manager, the device location manager operatively coupled to a position detection component of the multimodal device, the location change notification specifying a current location of the multimodal device, wherein the location change notification includes a timestamp specifying a time at which the multimodal device arrived at the current location;

identifying in a configuration parameter repository, location-based configuration parameters for the speech engine in dependence upon the current location of the multimodal device, the location-based configuration parameters specifying a configuration for the speech engine at the current location, wherein the location-based configuration parameters include an identifier for an acoustic model from among a plurality of acoustic models including a first acoustic model and a second acoustic model, an identifier for a lexicon from among a plurality of lexicons including a first lexicon and a second lexicon, speech transition times, silence detection times, speech timeouts, gain maps, and a configuration for use by a text-to-speech (‘TTS’) engine including a voice used in synthesizing speech from text, wherein each of the first acoustic model and the second acoustic model associates acoustic features with phonemes, wherein the first lexicon and the second lexicon specify a different phoneme representation for a same word; and

updating, by the location change monitor, a current configuration for the speech engine according to the identified location-based configuration parameters.

10. The computer readable recordable medium of claim 9 , wherein the first acoustic model and the second acoustic model associate different audio input with a same phoneme.

11. The computer readable recordable medium of claim 9 , wherein the location change notification includes a timestamp specifying a time at which the multimodal device arrived at the current location, and wherein identifying the location-based configuration parameters in the configuration parameter repository comprises identifying the location-based configuration parameters based, at least in part, on the timestamp specified in the location change notification and at least one previous timestamp included in a previous location change notification.