Abstract: A query parsing system uses a multi-stage process to parse the text of incoming queries before attempting to answer the queries. The multi-stage configuration involves a first trained classifier to determine the query type, or intent, of the text and a plurality of second trained classifiers, where each of the second trained classifiers is configured particularly for one specific respective query type. During query processing, the first trained classifier is used on the text to identify the query type. A second trained classifier for that specific identified query type is then found and used on the text to identify what strings in the text correspond to specific entities needed to resolve the query. The identified text strings and query type are then placed into a form understandable by a knowledge base and sent to the knowledge base for resolution. The classifiers may be trained using queries and answers previously processed by the knowledge base using a rules/template resolution process.

Abstract: Aspects of the disclosure provide suspension of noise cancellation at a noise-cancelling device using keyword spotting. In one aspect, a predetermined word or phrase can be spotted within an utterance received at the noise-cancelling device, and in response, noise cancellation can be suspended or otherwise terminated. The predetermined word or phrase can be specific to an end-user that utilizes the noise-cancelling device and/or a person that interacts with the end-user. In another aspect, interaction between an operator and the noise-cancelling device can be monitored after noise cancellation is suspended, and based at least on such interaction, a model for keyword spotting can be refined. In certain aspects, noise cancellation at the noise-cancelling device can be suspended or otherwise terminated in response to receiving a suspension directive via an electronic non-audio signal, for example, from a peripheral device.