Domain Language Models

See ASRaaS DLMs for more information.

The Krypton engine uses domain language models to identify the words and phrases most likely spoken by users of your application. Domain language models are overlaid on the factory or base data pack Krypton uses to provide a vocabulary for the application. You generate these custom models from training data that is representative of your application.

With the Mix Testing Tool you use more than one DLM (up to 5). To do so, specify each DLM URI as part of a list given via the dlm_uri parameter. The weight to use for each DLM can be listed respectively with the dlm_weight parameter. If only one weight is given, that weight will be passed to ASRaaS for all DLMs.

"asr": {
		"topic": "GEN",
		"dlm_weight": [
			0.2,
			0.05
		],
		"dlm_uri": [
			"urn:nuance-mix:tag:model/coffee_demo/mix.asr?=language=eng-USA",
			"urn:nuance-mix:tag:model/places/mix.asr?=language=eng-USA"
		],
		...
	}