Methods, systems, and computer-readable media for voice-activated selective memory for voice-capturing devices are disclosed. A first voice input from a voice-capturing device is received, via a network, at a service provider environment comprising one or more services. The first voice input comprises one or more utterances from a user of the voice-capturing device. A representation of the first voice input is stored. A second voice input from the voice-capturing device is received, via the network, at the service provider environment. The second voice input represents a command to disregard the first voice input. Based on the second voice input, the representation of the first voice input is deleted.

Methods, systems, and computer-readable media for voice-activated selective memory for voice-capturing devices are disclosed. A first voice input from a voice-capturing device is received, via a network, at a service provider environment comprising one or more services. The first voice input comprises one or more utterances from a user of the voice-capturing device. A representation of the first voice input is stored. A second voice input from the voice-capturing device is received, via the network, at the service provider environment. The second voice input represents a command to disregard the first voice input. Based on the second voice input, the representation of the first voice input is deleted.

Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.

Computer systems and computer-implemented methods provide for interactive and incremental post-editing of real-time speech transcription and translation. A first component is automatic identification of potentially problematic regions in the output (e.g., transcription or translation) that are either likely to be technically processed badly or risky in terms of their content or expression. A second component is intelligent, efficient interfaces that permit multiple editors to correct system output concurrently, collaboratively, efficiently, and simultaneously, so that corrections can be seamlessly inserted and become part of a running presentation. A third component is incremental learning and adaptation that allows the system to use the human corrective feedback to deliver instantaneous improvement of system behavior down-stream. A fourth component is transfer learning to transfer short-term learning into long term learning if the modifications warrant long-term retention.

Embodiments include methods and systems for improving an acoustic model. Aspects include acquiring a first standard deviation value by calculating standard deviation of a feature from first training data and acquiring a second standard deviation value by calculating standard deviation of a feature from second training data acquired in a different environment from an environment of the first training data. Aspects also include creating a feature adapted to an environment where the first training data is recorded, by multiplying the feature acquired from the second training data by a ratio obtained by dividing the first standard deviation value by the second standard deviation value. Aspects further include reconstructing an acoustic model constructed using training data acquired in the same environment as the environment of the first training data using the feature adapted to the environment where the first training data is recorded.

A voice to text model used by a voice-enabled electronic device is dynamically and in a context-sensitive manner updated to facilitate recognition of entities that potentially may be spoken by a user in a voice input directed to the voice-enabled electronic device. The dynamic update to the voice to text model may be performed, for example, based upon processing of a first portion of a voice input, e.g., based upon detection of a particular type of voice action, and may be targeted to facilitate the recognition of entities that may occur in a later portion of the same voice input, e.g., entities that are particularly relevant to one or more parameters associated with a detected type of voice action.

A voice to text model used by a voice-enabled electronic device is dynamically and in a context-sensitive manner updated to facilitate recognition of entities that potentially may be spoken by a user in a voice input directed to the voice-enabled electronic device. The dynamic update to the voice to text model may be performed, for example, based upon processing of a first portion of a voice input, e.g., based upon detection of a particular type of voice action, and may be targeted to facilitate the recognition of entities that may occur in a later portion of the same voice input, e.g., entities that are particularly relevant to one or more parameters associated with a detected type of voice action.

A method for training parameters of a first domain adaptation model. The method includes evaluating a cycle consistency objective using a first task specific model associated with a first domain and a second task specific model associated with a second domain, and evaluating one or more first discriminator models to generate a first discriminator objective using the second task specific model. The one or more first discriminator models include a plurality of discriminators corresponding to a plurality of bands that corresponds domain variable ranges of the first and second domains respectively. The method further includes updating, based on the cycle consistency objective and the first discriminator objective, one or more parameters of the first domain adaptation model for adapting representations from the first domain to the second domain.

A method for training parameters of a first domain adaptation model. The method includes evaluating a cycle consistency objective using a first task specific model associated with a first domain and a second task specific model associated with a second domain, and evaluating one or more first discriminator models to generate a first discriminator objective using the second task specific model. The one or more first discriminator models include a plurality of discriminators corresponding to a plurality of bands that corresponds domain variable ranges of the first and second domains respectively. The method further includes updating, based on the cycle consistency objective and the first discriminator objective, one or more parameters of the first domain adaptation model for adapting representations from the first domain to the second domain.

Techniques performed by a data processing system for processing voice content received from a user herein include receiving a first audio input from the user comprising a mixed-mode dictation, analyzing, using one or more machine learning (ML) models, the first audio input to obtain a first interpretation of the mixed-mode dictation, presenting the first interpretation to the user in an application on the data processing system, receiving a second audio input from the user comprising a corrective command, analyzing the second audio input to obtain a second interpretation of the restatement of the mixed-mode dictation presenting the second interpretation to the user, receiving an indication from the user that the second interpretation is a correct interpretation of the mixed-mode dictation, and modifying the operating parameters of the one or more machine learning models to interpret the subsequent instances of the mixed-mode dictation based on the second interpretation.