Methods, systems, and computer readable media for automated transcription model adaptation includes obtaining audio data from a plurality of audio files. The audio data is transcribed to produce at least one audio file transcription which represents a plurality of transcription alternatives for each audio file. Speech analytics are applied to each audio file transcription. A best transcription is selected from the plurality of transcription alternatives for each audio file. Statistics from the selected best transcription are calculated. An adapted model is created from the calculated statistics.

Methods and systems are provided for generating a customized speech recognition neural network system comprised of an adapted automatic speech recognition neural network and an adapted language model neural network. The automatic speech recognition neural network is first trained in a generic domain and then adapted to a target domain. The language model neural network is first trained in a generic domain and then adapted to a target domain. Such a customized speech recognition neural network system can be used to understand input vocal commands.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modulating language model biasing. In some implementations, context data is received. A likely context associated with a user is determined based on at least a portion of the context data. One or more language model biasing parameters based at least on the likely context associated with the user is selected. A context confidence score associated with the likely context based on at least a portion of the context data is determined. One or more language model teasing parameters based at least on the context confidence score is adjusted. A baseline language model based at least on the one or more of the adjusted language model biasing parameters is biased. The baseline language model is provided for use by an automated speech recognizer (ASR).

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for modulating language model biasing. In some implementations, context data is received. A likely context associated with a user is determined based on at least a portion of the context data. One or more language model biasing parameters based at least on the likely context associated with the user is selected. A context confidence score associated with the likely context based on at least a portion of the context data is determined. One or more language model teasing parameters based at least on the context confidence score is adjusted. A baseline language model based at least on the one or more of the adjusted language model biasing parameters is biased. The baseline language model is provided for use by an automated speech recognizer (ASR).

Text independent speaker recognition models can be utilized by an automated assistant to verify a particular user spoke a spoken utterance and/or to identify the user who spoke a spoken utterance. Implementations can include automatically updating a speaker embedding for a particular user based on previous utterances by the particular user. Additionally or alternatively, implementations can include verifying a particular user spoke a spoken utterance using output generated by both a text independent speaker recognition model as well as a text dependent speaker recognition model. Furthermore, implementations can additionally or alternatively include prefetching content for several users associated with a spoken utterance prior to determining which user spoke the spoken utterance.

Text independent speaker recognition models can be utilized by an automated assistant to verify a particular user spoke a spoken utterance and/or to identify the user who spoke a spoken utterance. Implementations can include automatically updating a speaker embedding for a particular user based on previous utterances by the particular user. Additionally or alternatively, implementations can include verifying a particular user spoke a spoken utterance using output generated by both a text independent speaker recognition model as well as a text dependent speaker recognition model. Furthermore, implementations can additionally or alternatively include prefetching content for several users associated with a spoken utterance prior to determining which user spoke the spoken utterance.

A voice command system according to a first disclosure comprises a gateway apparatus having an interface configured to receive a voice command, and a controller configured to perform a registration process of registering a speaker permitted to receive the voice command. The controller is configured to perform an authentication process of rejecting a reception of the voice command when a speaker of the voice command is not registered, and permitting a reception of the voice command when a speaker of the voice command is registered. The controller is configured to perform the authentication process for each voice command.

A voice command system according to a first disclosure comprises a gateway apparatus having an interface configured to receive a voice command, and a controller configured to perform a registration process of registering a speaker permitted to receive the voice command. The controller is configured to perform an authentication process of rejecting a reception of the voice command when a speaker of the voice command is not registered, and permitting a reception of the voice command when a speaker of the voice command is registered. The controller is configured to perform the authentication process for each voice command.

Disclosed is gathering a user's speech samples. According to an embodiment of the disclosure, a method of gathering learning samples may gather a speaker's speech data obtained while talking on a mobile terminal and text data generated from the speech data and gather training data for generating a speech synthesis model. According to the disclosure, the method of gathering learning samples may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

A computer system and method transcribe a spoken dialogue, such as a dialogue between a physician and a patient, into a document, such as a clinical note. As the document is generated, if content is detected in the dialog which corresponds to a content template, the content template is inserted into the document. Fields in the content template may also be filled using information from the dialog and/or information external to the dialog.