A method to transcribe communications may include obtaining, at a first device, an audio signal that originates at a remote device during a communication session. The audio signal may be shared between the first device and a second device. The method may also include obtaining an indication that the second device is associated with a remote transcription system and in response to the second device being associated with the remote transcription system, directing the audio signal to the remote transcription system by one of the first device and the second device instead of both the first device and the second device directing the audio signal to the remote transcription system when the second device is not associated with the remote transcription system.

A method to transcribe communications may include obtaining, at a first device, an audio signal that originates at a remote device during a communication session. The audio signal may be shared between the first device and a second device. The method may also include obtaining an indication that the second device is associated with a remote transcription system and in response to the second device being associated with the remote transcription system, directing the audio signal to the remote transcription system by one of the first device and the second device instead of both the first device and the second device directing the audio signal to the remote transcription system when the second device is not associated with the remote transcription system.

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.

An artificial intelligence device includes a microphone configured to receive a speech command, a speaker, a communication unit configured to perform communication with an external artificial intelligence device, and a processor configured to receive a wake-up command through the microphone, acquire a first speech quality level of the received wake-up command, receive a second speech quality level of the wake-up command input to the external artificial intelligence device from the external artificial intelligence device through the communication unit, output a notification indicating that the artificial intelligence device is selected as an object to be controlled through the speaker, when the first speech quality level is larger than the second speech quality level, receive an operation command through the microphone, acquire an intention of the received operation command and transmit the operation command to an external artificial intelligence device which will perform operation corresponding to the operation command according to the acquired intention through the communication unit.

A method includes training a set of teacher models. Training the set of teacher models includes, for each individual teacher model of the set of teacher models, training the individual teacher model to transcribe unlabeled audio samples and predict a pseudo labeled dataset having multiple labels. At least some of the unlabeled audio samples contain named entity (NE) audio data. At least some of the labels include transcribed NE labels corresponding to the NE audio data. The method also includes correcting at least some of the transcribed NE labels using user-specific NE textual data. The method further includes retraining the set of teacher models based on the pseudo labeled dataset from a selected one of the teacher models, where the selected one of the teacher models predicts the pseudo labeled dataset more accurately than other teacher models of the set of teacher models.

Techniques are described herein for detecting and handling failures in other automated assistants. A method includes: executing a first automated assistant in an inactive state at least in part on a computing device operated by a user; while in the inactive state, determining, by the first automated assistant, that a second automated assistant failed to fulfill a request of the user; in response to determining that the second automated assistant failed to fulfill the request of the user, the first automated assistant processing cached audio data that captures a spoken utterance of the user comprising the request that the second automated assistant failed to fulfill, or features of the cached audio data, to determine a response that fulfills the request of the user; and providing, by the first automated assistant to the user, the response that fulfills the request of the user.

Techniques are described herein for detecting and handling failures in other automated assistants. A method includes: executing a first automated assistant in an inactive state at least in part on a computing device operated by a user; while in the inactive state, determining, by the first automated assistant, that a second automated assistant failed to fulfill a request of the user; in response to determining that the second automated assistant failed to fulfill the request of the user, the first automated assistant processing cached audio data that captures a spoken utterance of the user comprising the request that the second automated assistant failed to fulfill, or features of the cached audio data, to determine a response that fulfills the request of the user; and providing, by the first automated assistant to the user, the response that fulfills the request of the user.

A speech recognition method includes receiving speech data, obtaining, from the received speech data, a candidate text including at least one word and a phonetic symbol sequence associated with a pronunciation of a target word included in the received speech data, using a speech recognition model, replacing the phonetic symbol sequence included in the candidate text with a replacement word corresponding to the phonetic symbol sequence, and determining a target text corresponding to the received speech data based on a result of the replacing.

Methods, apparatus, systems and articles of manufacture are disclosed. An example apparatus includes a controller to cause a people meter to emit a prompt for input of audience identification information at a first time and determine a first audience count based on the input, an audio detector to determine a second audience count based on signatures generated from audio data captured in the media environment, and a comparator to cause the people meter to not emit the prompt for at least a first time period after the first time when the first audience count is equal to the second audience count.

Methods, apparatus, systems and articles of manufacture are disclosed. An example apparatus includes a controller to cause a people meter to emit a prompt for input of audience identification information at a first time and determine a first audience count based on the input, an audio detector to determine a second audience count based on signatures generated from audio data captured in the media environment, and a comparator to cause the people meter to not emit the prompt for at least a first time period after the first time when the first audience count is equal to the second audience count.