Abstract: A method for performing domain adaptation of an end-to-end (E2E) automatic speech recognition (ASR) model. The method includes: obtaining an un-adapted version of the E2E ASR model trained using a first set of transcriptions, the un-adapted version of E2E ASR model including an encoder network, a first prediction network and a joint network; using the first set of transcriptions, while keeping parameters of first prediction network fixed, to train a language model output component to match the first prediction network; using a second set of transcriptions, while keeping parameters of language model output component fixed, to fine-tune the first prediction network for obtaining a second prediction network; and generating an adapted version of the E2E ASR model, wherein the adapted version of the E2E ASR model comprises the encoder network, the second prediction network, the language model output component, and the joint network.

Abstract: A method for performing domain adaptation of an end-to-end (E2E) automatic speech recognition (ASR) model. The method includes: obtaining an un-adapted version of the E2E ASR model trained using a first set of transcriptions, the un-adapted version of E2E ASR model including an encoder network, a first prediction network and a joint network; using the first set of transcriptions, while keeping parameters of first prediction network fixed, to train a language model output component to match the first prediction network; using a second set of transcriptions, while keeping parameters of language model output component fixed, to fine-tune the first prediction network for obtaining a second prediction network; and generating an adapted version of the E2E ASR model, wherein the adapted version of the E2E ASR model comprises the encoder network, the second prediction network, the language model output component, and the joint network.

Abstract: A method for voice recognition to perform an action. The method includes receiving a voice command, identifying a first action intended word from the voice command, assigning a confidence score to the first action intended word, altering the confidence score of the first action intended word in a temporal manner, based on confidence scores of second action intended words following the first action intended word in the voice command, identifying the action when the confidence scores of the first and second action intended words reach a pre-determined confidence score associated therewith, and performing the identified action. Disclosed also is a system for voice recognition to perform an action. The system includes one or more voice-controlled devices, and a voice managing server communicably coupled to the one or more voice-controlled devices. The voice managing server for voice recognition to perform an action using the aforementioned method.

Abstract: A method for modifying user-interface using voice commands. Method includes receiving first and second voice commands of first type respectively at first and second moments of time for creating first and second user-interface elements including first and second information having at least one information attribute associated therewith; receiving third voice command of second type at third moment of time for initiating modification process for modifying first or second user-interface elements; and rendering modified user-interface element on user-interface.

Abstract: Embodiments disclosed herein may relate to extracting tips from online sources and/or selecting tips for display to a user on a computing platform.