Dynamic speech recognition methods and systems with user-configurable performance

A non-transitory computer-readable medium having computer-executable instructions stored thereon that, when executed by a processing system, cause the processing system to:

• dynamically identify a current user-configured speech recognition performance setting value selected from among a plurality of speech recognition performance setting values associated with a current operational context during operation of a vehicle;
• select a speech recognition model configuration corresponding to the current user-configured speech recognition performance setting value from among a plurality of speech recognition model configurations by mapping the current user-configured speech recognition performance setting value to a combination of an acoustic model from among a plurality of different acoustic models and a language model from among a plurality of different language models, wherein each speech recognition model configuration of the plurality of speech recognition model configurations comprises a different combination of a respective acoustic model of the plurality of different acoustic models and a respective language model of the plurality of different language models corresponding to a respective one of the plurality of speech recognition performance setting values;
• and
• recognize an audio input as an input command using the speech recognition model configuration corresponding to the current user-configured speech recognition performance setting value by:
• converting the audio input into a textual representation comprising a probable combination of words using the acoustic model associated with the speech recognition model configuration corresponding to the current user-configured speech recognition performance setting value;
• and
• converting the textual representation into the input command using the language model associated with the speech recognition model configuration corresponding to the current user-configured speech recognition performance setting value.

A system comprising:

• a user interface comprising a user interface element for selecting a current speech recognition performance setting value from among a plurality of speech recognition performance setting values to be associated with a current operational context during operation of a vehicle;
• a data storage element to maintain a plurality of speech recognition models for a plurality of speech recognition model configurations, wherein each speech recognition model configuration of the plurality of speech recognition model configurations corresponds to a respective one of the plurality of speech recognition performance setting values and each speech recognition model configuration of the plurality of speech recognition model configurations corresponds to a different combination of a respective acoustic model of a plurality of different acoustic models and a respective language model of a plurality of different language models;
• an audio input device to receive an audio input;
• and
• a processing system coupled to the audio input device, the data storage element and the user interface to select a respective combination of one or more speech recognition models of the plurality of speech recognition models for a respective speech recognition model configuration corresponding to the current speech recognition performance setting value selected by the user interface element and recognizing the audio input as an input command using the respective combination of one or more speech recognition models by converting the audio input into a textual representation comprising a probable combination of words using the acoustic model associated with the speech recognition model configuration corresponding to the current speech recognition performance setting value and converting the textual representation into the input command using the language model associated with the speech recognition model configuration corresponding to the current speech recognition performance setting value.