Google Inc.

Telefonaktiebolaget Lm Ericsson (Publ)

Mk Systems USA Inc.

Mk Mediakind Systems Israel Ltd

Tomer Amiaz

Asaf Aharoni

Yaniv Leviathan

Pedro Jose Moreno Mengibar

Rohit Prakash Prabhavalkar

Arun Narayanan

Neeraj Gaur

Parisa Haghani

Nir Shabat

Austin Severn Waters

Galen Tsai Chuang

Zhongdi Qu

Eyal Segalis

Michiel A U Bacchiani

Sasha Goldshtein

Volodya Grancharov

Harald Pobloth

Hadar Gecht

Ofer Ron

Golan Pundak

Anthony Richard Jones

Razvan Mathias

Deborah Cohen

Gal Elidan

Dan Rasin

Rafael Goldfarb

Or Guz

Assaf Hurwitz Michaely

Lior Alon

Michiel Au Bacchiani

Shmuel Leibtag

Implementations are directed to causing a voice bot to utilize a plurality of ML layers in resolving unique personal identifier(s) for a human while the voice bot is engaged in a corresponding conversation with the human. The unique personal identifier(s) can include a unique sequence of alphanumeric characters that is personal to the human. In some implementations, ASR speech hypothes(es) corresponding to spoken utterance(s) that include the unique personal identifier(s) can be processed to generate candidate unique personal identifier(s), given alphanumeric character(s) of the candidate unique personal identifier(s) can be selected, and the voice bot can prompt the human with clarification request(s) to clarify the given alphanumeric character(s) until it is predicted to correspond to the an actual unique personal identifier(s) for the human(s). The unique personal identifier(s) can then be utilized in performance of further action(s) by the voice bot and/or other systems.

Resolving unique personal identifiers during corresponding conversations between a voice bot and a human

Implementations are directed to providing a voice bot development platform that enables a third-party developer to train a voice bot based on training instance(s). The training instance(s) can each include training input and training output. The training input can include a portion of a corresponding conversation and a prior context of the corresponding conversation. The training output can include a corresponding ground truth response to the portion of the corresponding conversation. Subsequent to training, the voice bot can be deployed for conducting conversations on behalf of a third-party. In some implementations, the voice bot is further trained based on a corresponding feature emphasis input that attentions the voice bot to a particular feature of the portion of the corresponding conversation. In some additional or alternative implementations, the voice bot is further trained to interact with third-party system(s) via remote procedure calls (RPCs).

Example-based voice bot development techniques

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an automated calling system are disclosed. In one aspect, a method includes the actions of receiving audio data of an utterance spoken by a user who is having a telephone conversation with a bot. The actions further include determining a context of the telephone conversation. The actions further include determining a user intent of a first previous portion of the telephone conversation spoken by the user and a bot intent of a second previous portion of the telephone conversation outputted by a speech synthesizer of the bot. The actions further include, based on the audio data of the utterance, the context of the telephone conversation, the user intent, and the bot intent, generating synthesized speech of a reply by the bot to the utterance. The actions further include, providing, for output, the synthesized speech.

Automated calling system

Implementations are directed to updating a trained voice bot that is deployed for conducting conversations on behalf of a third-party. A third-party developer can interact with a voice bot development system that enables the third-party developer to train, update, validate, and monitor performance of the trained voice bot. In various implementations, the trained voice bot can be updated by updating a corpus of training instances that was initially utilized to train the voice bot, and updating the trained voice bot based on the updated corpus. In some implementations, the corpus of training instances may be updated in response to identifying occurrence(s) of behavioral error(s) of the trained voice bot while the conversations are being conducted on behalf of the third-party. In additional or alternative implementations, the corpus of training instances may be updated in response to determining the trained voice bot does not include a desired behavior.

Updating trained voice bot(s) utilizing example-based voice bot development techniques

A network node in a communication network receives, from a user equipment, a cluster of audio segments. The network node calculates a first confidence measure representing a first probability that a first speaker model represents a speaker of the cluster of audio segments. The network node also calculates a second confidence measure representing a second probability that a second speaker model represents the speaker of the cluster of audio segments. In response to the first confidence measure and the second confidence measure both representing probabilities that are higher than a target probability, the network node updates a first user profile associated with the first speaker model and a second user profile associated with the second speaker model based on a user preference assigned to the cluster of audio segments.

Voice-controlled management of user profiles

A management of user profiles comprises calculating, for an audio segment, a user confidence measure representing a probability that the audio segment comprises speech of a user and a group confidence measure representing a probability that the audio segment comprises speech of a group of users. A user profile is then managed based on a comparison between the user confidence measure and a user confidence threshold and between the group confidence measure and a group confidence threshold. The embodiments thereby achieve an efficient voice-controlled user profile management by utilizing a layered approach that provides user profiles for group of users as fallback when the identity of the speaking user can not accurately be recognized.

A management of user profiles comprises calculating, for each speaker model of at least one speaker model, a confidence measure representing a probability that the speaker model represents a speaker of a cluster of audio segments. A user profile associated with the speaker model is updated based on a user preference assigned to the cluster of audio segments if the confidence measure calculated for the speaker model represents a probability that is higher than a target probability. The embodiments achieve an efficient user profile management in a voice-controlled context but without the need for any dedicated enrollment sessions to train speaker models.

A method in an encoder, the method comprising: receiving a video; encoding a segment of the video at different bit rates to generate multiple representations of the segment at different bit rates; generating a quality metric for each representation of the video segment; and storing the lowest bit rate representation of the video segment for which the respective quality metric meets a predefined minimum quality threshold.

Cloud DVR storage

Growing community of inventors

Tel Aviv, Israel

Tomer Amiaz