An electronic apparatus includes: a memory storing one or more commands; and a processor connected to the memory and configured to control the electronic apparatus, wherein the processor is configured, by executing the one or more instructions, to: identify a first intention word and a first target word from first speech, acquire second speech received after the first speech based on at least one of the identified first intention word or the identified first target word not matching a word stored in the memory, acquire a similarity between the first speech and the second speech, and acquire response information based on the first speech and the second speech based on the similarity being a threshold value or more.

Systems and processes for operating a digital assistant are provided. An example process for performing a task includes, at an electronic device having one or more processors and memory, receiving a spoken input including a request, receiving an image input including a plurality of objects, selecting a reference resolution module of a plurality of reference resolution modules based on the request and the image input, determining, with the selected reference resolution module, whether the request references a first object of the plurality of objects based on at least the spoken input, and in accordance with a determination that the request references the first object of the plurality of objects, determining a response to the request including information about the first object.

The disclosure provides a multimodal speech recognition method and system, and a computer-readable storage medium. The method includes calculating a first logarithmic mel-frequency spectral coefficient and a second logarithmic mel-frequency spectral coefficient when a target millimeter-wave signal and a target audio signal both contain speech information corresponding to a target user; inputting the first and the second logarithmic mel-frequency spectral coefficient into a fusion network to determine a target fusion feature, where the fusion network includes at least a calibration module and a mapping module, the calibration module is configured to perform mutual feature calibration on the target audio/millimeter-wave signals, and the mapping module is configured to fuse a calibrated millimeter-wave feature and a calibrated audio feature; and inputting the target fusion feature into a semantic feature network to determine a speech recognition result corresponding to the target user. The disclosure can implement high-accuracy speech recognition.

Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

Embodiments are directed to organizing conversation information. A tracker vocabulary may be provided to a universal model to predict a generalized vocabulary associated with the tracker vocabulary. A tracker model may be generated based on the portions of the universal model activated by the tracker vocabulary such that a remainder of the universal model may be excluded from the tracker model. Portions of a conversation stream may be provided to the tracker model. A match score may be generated based on the track model and the portions of the conversation stream such that the match score predicts if the portions of the conversation stream may be in the generalized vocabulary predicted for the tracker vocabulary. Tracker metrics may be collected based on the portions of the conversation and the match scores such that the tracker metrics may be included in reports or notifications.

A method and apparatus for generating a user intention understanding satisfaction evaluation model, a method and apparatus for evaluating a user intention understanding satisfaction, an electronic device and a storage medium are provided, relating to intelligent voice recognition and knowledge graphs. The method for generating a user intention understanding satisfaction evaluation model is: acquiring a plurality of sets of intention understanding data, at least one set of which comprises a plurality of sequences corresponding to multi-round behaviors of an intelligent device in multi-round man-machine interactions; and learning the plurality of sets of intention understanding data through a first machine learning model, to obtain the user intention understanding satisfaction evaluation model after the learning, wherein the user intention understanding satisfaction evaluation model is configured to evaluate user intention understanding satisfactions of the intelligent device in the multi-round man-machine interactions according to the plurality of sequences corresponding to the multi-round man-machine interactions.

An electronic apparatus is provided. The electronic apparatus includes a microphone, a memory configured to store a plurality of keyword recognition models, and a processor, which is coupled with the microphone and the memory, configured to control the electronic apparatus, wherein the processor is configured to selectively execute at least one keyword recognition model among the plurality of keyword recognition models based on operating state information of the electronic apparatus, based on a first user voice being input through the microphone, identify whether at least one keyword corresponding to the executed keyword recognition model is included in the first user voice by using the executed keyword recognition model, and based on at least one keyword identified as being included in the first user voice, perform an operation of the electronic apparatus corresponding to the at least one keyword.

Embodiments described herein provide a dynamic topic tracking mechanism that tracks how the conversation topics change from one utterance to another and use the tracking information to rank candidate responses. A pre-trained language model may be used for response selection in the multi-party conversations, which consists of two steps: (1) a topic-based pre-training to embed topic information into the language model with self-supervised learning, and (2) a multi-task learning on the pretrained model by jointly training response selection and dynamic topic prediction and disentanglement tasks.

Provided is an in-ear device and associated computational support system that leverages machine learning to interpret sensor data descriptive of one or more in-ear phenomena during subvocalization by the user. An electronic device can receive sensor data generated by at least one sensor at least partially positioned within an ear of a user, wherein the sensor data was generated by the at least one sensor concurrently with the user subvocalizing a subvocalized utterance. The electronic device can then process the sensor data with a machine-learned subvocalization interpretation model to generate an interpretation of the subvocalized utterance as an output of the machine-learned subvocalization interpretation model.