Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Techniques are disclosed that enable generation of an audio waveform representing synthesized speech based on a difference signal determined using an autoregressive model. Various implementations include using a distribution of the difference signal values to represent sounds found in human speech with a higher level of granularity than sounds not frequently found in human speech. Additional or alternative implementations include using one or more speakers of a client device to render the generated audio waveform.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output audio examples using a generative neural network. One of the methods includes obtaining a training conditioning text input; processing a training generative input comprising the training conditioning text input using a feedforward generative neural network to generate a training audio output; processing the training audio output using each of a plurality of discriminators, wherein the plurality of discriminators comprises one or more conditional discriminators and one or more unconditional discriminators; determining a first combined prediction by combining the respective predictions of the plurality of discriminators; and determining an update to current values of a plurality of generative parameters of the feedforward generative neural network to increase a first error in the first combined prediction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.

Abstract: Speaker diarization techniques that enable processing of audio data to generate one or more refined versions of the audio data, where each of the refined versions of the audio data isolates one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by generating a speaker embedding for the single human speaker, and processing the audio data using a trained generative model—and using the speaker embedding in determining activations for hidden layers of the trained generative model during the processing. Output is generated over the trained generative model based on the processing, and the output is the refined version of the audio data.

Abstract: Automated monitoring of a voice communication session, when the session is in an on hold status, to determine when the session is no longer in the on hold status. When it is determined that the session is no longer in the on hold status, user interface output is rendered that is perceptible to a calling user that initiated the session, and that indicates that the on hold status of the session has ceased. In some implementations, an audio stream of the session can be monitored to determine, based on processing of the audio stream, a candidate end of the on hold status. In response, a response solicitation signal is injected into an outgoing portion of the audio. The audio stream can be further monitored for a response (if any) to the response solicitation signal. The response (if any) can be processed to determine whether the end of the on hold status is an actual end of the on hold status.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.