Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

Abstract: As part of an ongoing dialog between a user and an automated assistant, processor(s) can receive a natural language (NL) based input from the user during a turn of the ongoing dialog, obtain style signal(s) for the turn, and determine, based on the style signal(s), a NL based response style that is not specified in the NL based input. Further, the processor(s) can process, using a large language model (LLM), the NL based input and a NL based response style tag for the NL based response style to generate LLM output, determine, based on the LLM output, a NL based response in the NL based response style, and cause the NL based response to be rendered. In some implementations, a LLM behavior controller is utilized to determine the NL based response style, whereas in other implementations, the LLM is fine-tuned to determine the NL based response style.

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

Abstract: A system and method for localizing a spoken dialog system is disclosed. Source data from a source language spoken dialog system is accessed, including semantic annotations and transcriptions of a plurality of utterances. The transcriptions are machine-translated into a target language. Semantic classifiers are trained on the machine translated transcriptions and the source language semantic annotations.

Abstract: A persistent companion robot supports both one-on-one interaction with a human and group interaction with more than one human. The interaction can be directed to a human in detectable proximity, such as a human that is near to the robot, one that is further away from the robot, or any combination of near and far humans. The interaction incorporates multi-modal human input detection (e.g., seeing, hearing, tactile) with multi-modal expression (e.g., movement, speech, non-speech sound, lighting, electronic imagery, and the like.

Abstract: Tiled grammar-based phrase spotting includes orienting at least one segment of a multi-segment robot to facilitate capturing speech of a user arriving at the robot, and configuring a plurality of processing threads of a multi-threaded processing environment into distinct tiles, wherein at least a portion of the plurality of processing threads operate simultaneously on the captured speech to recognize a phrase type using a speech recognition grammar that is associated with the corresponding tile, wherein at least two of the tiles employ different speech recognition grammars to recognize different content in the captured speech.

Abstract: A method includes steps of indexing a media collection, searching an indexed library and browsing a set of candidate program segments. The step of indexing a media collection creates the indexed library based on a content of the media collection. The step of searching the indexed library identifies the set of candidate program segments based on a search criteria. The step of browsing the set of candidate program segments selects a segment for viewing.

Abstract: A method includes steps of indexing a media collection, searching an indexed library and browsing a set of candidate program segments. The step of indexing a media collection creates the indexed library based on a content of the media collection. The step of searching the indexed library identifies the set of candidate program segments based on a search criteria. The step of browsing the set of candidate program segments selects a segment for viewing.

Abstract: An embodiment of the invention is a software tool used to convert text, speech synthesis markup language (SSML), and/or extended SSML to synthesized audio. Provisions are provided to create, view, play, and edit the synthesized speech, including editing pitch and duration targets, speaking type, paralinguistic events, and prosody. Prosody can be provided by way of a sample recording. Users can interact with the software tool by way of a graphical user interface (GUI). The software tool can produce synthesized audio file output in many file formats.

Abstract: A dialog manager for a spoken dialog system. A decision module selects a path from a plurality of alternative paths for a given call, wherein each path implements one of a plurality of strategies for a call flow. A weighting module weights the path selection decision and is connected to a probability estimator for estimating the probability value that a given one of the plurality of paths is the best-performing path.

Abstract: A system and a method to generate statistical utterance classifiers optimized for the individual states of a spoken dialog system is disclosed. The system and method make use of large databases of transcribed and annotated utterances from calls collected in a dialog system in production and log data reporting the association between the state of the system at the moment when the utterances were recorded and the utterance. From the system state, being a vector of multiple system variables, subsets of these variables, certain variable ranges, quantized variable values, etc. can be extracted to produce a multitude of distinct utterance subsets matching every possible system state. For each of these subset and variable combinations, statistical classifiers can be trained, tuned, and tested, and the classifiers can be stored together with the performance results and the state subset and variable combination.

Abstract: An embodiment of the invention is a software tool used to convert text, speech synthesis markup language (SSML), and/or extended SSML to synthesized audio. Provisions are provided to create, view, play, and edit the synthesized speech, including editing pitch and duration targets, speaking type, paralinguistic events, and prosody. Prosody can be provided by way of a sample recording. Users can interact with the software tool by way of a graphical user interface (GUI). The software tool can produce synthesized audio file output in many file formats.

Abstract: A method and apparatus for continuously improving the performance of semantic classifiers in the scope of spoken dialog systems are disclosed. Rule-based or statistical classifiers are replaced with better performing rule-based or statistical classifiers and/or certain parameters of existing classifiers are modified. The replacement classifiers or new parameters are trained and tested on a collection of transcriptions and annotations of utterances which are generated manually or in a partially automated fashion. Automated quality assurance leads to more accurate training and testing data, higher classification performance, and feedback into the design of the spoken dialog system by suggesting changes to improve system behavior.

Abstract: A single, subjective numerical rating to evaluate the performance of a telephone-based spoken dialog system. This CE rating is provided by expert human listeners who have knowledge of the design of the dialog system. Different human raters can be trained to achieve a satisfactory level of agreement. Furthermore, a classifier trained on ratings by human experts can reproduce the human ratings with the same degree of consistency. More calls can be given a CE rating than would be possible with limited human resources. More information can be provided about individual calls, e.g., to help decide between two disparate ratings by different human experts.