Abstract: Systems and methods for determining, based on invocation input that is common to multiple automated assistants, which automated assistant to invoke in lieu of invoking other automated assistants. The invocation input is processed to determine one or more invocation features that may be utilized to determine which, of a plurality of candidate automated assistants, to invoke. Further, additional features are processed that can indicate which, of the plurality of invocable automated assistants, to invoke. Once an automated assistant has been invoked, additional audio data and/or features of additional audio data are provided to the invoked automated assistant for further processing.

Abstract: Dependency trees are generated for questions and answers of a question answering (QA) corpus in which the answers are associated with the questions. Generating the dependency trees includes identifying root nodes. A word near an identified root node of one of the questions is compared to words of answers associated with the one of the questions. The word is determined to be in less than a threshold number of the associated answers. The word is identified as a stop word.

Abstract: Methods and systems are disclosed configured to perform automated volume leveling on speech content in an audio file containing speech and non-speech segments. A low pass filter and a high pass filter may be applied to the audio data, and normalization may be performed. Speech and non-speech segments may be detected. Gain adjustments may be made to achieve a substantially constant short term loudness. Processing may be applied to enhance speech parameters, such as attack and release. An upward expander may be used to achieve a target loudness level. A limited and/or dynamic range compressor may be utilized to satisfy true peak and/or short term loudness specifications. A file of processed audio data may be generated and transmitted to one or more destinations for broadcast and/or streaming.

Abstract: An autonomous agent receives a user query comprising the complex question. The agent can obtain, from a corpus of unstructured texts, an answer candidate text corresponding to the user query and comprising text from which the answer is subsequently identified. The agent may generate first linguistic data corresponding to the user query and second linguistic data corresponding to the answer candidate text. Each instance of linguistic data may comprise a combination of respective syntactic data, semantic data, and discourse data generated from the user query and/or answer candidate text. Both instances of linguistic data may be provided to a machine-learning model that has been previously trained to output an answer identified from an instance of unstructured text (e.g., the answer candidate text). The model may output the answer identified from the answer candidate text, which in turn may be provided in response to the user query.

Abstract: Disclosed is a dialogue emotion correction method based on a graph neural network, including: extracting acoustic features, text features, and image features from a video file to fuse them into multi-modal features; obtaining an emotion prediction result of each sentence of a dialogue in the video file by using the multi-modal features; fusing the emotion prediction result of each sentence with interaction information between talkers in the video file to obtain interaction information fused emotion features; combining, on the basis of the interaction information fused emotion features, with context-dependence relationship in the dialogue to obtain time-series information fused emotion features; correcting, by using the time-series information fused emotion features, the emotion prediction result of each sentence that is obtained previously as to obtain a more accurate emotion recognition result.

Abstract: As an example, a server may receive, from a computing device, a submission created by an author. The submission includes book data associated with a book and author data associated with the author. The author data includes incarceration data indicating whether the author was incarcerated. The server may determine, based on the author data and the book data, that the submission is publishable. The server may create, based on the book data, a printable book, an e-book, and an audio book and make one or more of the printable book, the e-book, and the audio book available for acquisition.