Google Inc.

Taral Pradeep Joglekar

Alexander Houston Gruenstein

Ignacio Lopez Moreno

Diego Melendo Casado

Michiel A U Bacchiani

Pu-sen Chao

Meltem Oktem

Vijayaditya Peddinti

Salil Rajadhyaksha

Fnu Heryandi

Hasim Sak

Quan Wang

Anshuman Tripathi

Han Lu

Wei Xia

Evan Clark

Pu-Sen Chao

Michiel AU Bacchiani

A method includes receiving an input audio signal that corresponds to utterances spoken by multiple speakers. The method also includes processing the input audio to generate a transcription of the utterances and a sequence of speaker turn tokens each indicating a location of a respective speaker turn. The method also includes segmenting the input audio signal into a plurality of speaker segments based on the sequence of speaker tokens. The method also includes extracting a speaker-discriminative embedding from each speaker segment and performing spectral clustering on the speaker-discriminative embeddings to cluster the plurality of speaker segments into k classes. The method also includes assigning a respective speaker label to each speaker segment clustered into the respective class that is different than the respective speaker label assigned to the speaker segments clustered into each other class of the k classes.

Speaker-turn-based online speaker diarization with constrained spectral clustering

A method includes adding, by a first computing device, a first audio watermark to first speech data corresponding to playback of a first utterance including a hotword used to invoke an attention of a second computing device. The method includes outputting, by the first computing device, the playback of the first utterance corresponding to the watermarked first speech data. The second computing device is configured to receive the watermarked first speech data and determine to cease processing of the watermarked first speech data.

Hotword suppression

In some implementations, processor(s) can receive an utterance from a speaker, and determine whether the speaker is a known user of a user device or not a known user of the user device. The user device can be shared by a plurality of known users. Further, the processor(s) can determine whether the utterance corresponds to a personal request or non-personal request. Moreover, and in response to determining that the speaker is not a known user of the user device and in response to determining that the utterance corresponds to a non-personal request, the processor(s) can cause a response to the utterance to be provided for presentation to the speaker at the user device response to the utterance, or can cause an action to be performed by the user device responsive to the utterance.

Multi-user authentication on a device

A method includes obtaining, by data processing hardware, a plurality of non-watermarked speech samples. Each non-watermarked speech does not include an audio watermark sample. The method includes, from each non-watermarked speech sample of the plurality of non-watermarked speech samples, generating one or more corresponding watermarked speech samples that each include at least one audio watermark. The method includes training, using the plurality of non-watermarked speech samples and corresponding watermarked speech samples, a model to determine whether a given audio data sample includes an audio watermark, and after training the model, transmitting the trained model to a user computing device.

In some implementations, authentication tokens corresponding to known users of a device are stored on the device. An utterance from a speaker is received. The speaker of the utterance is classified as not a known user of the device. A query that includes the authentication tokens that correspond to known users of the device, a representation of the utterance, and an indication that the speaker was classified as not a known user of the device is provided to the server. A response to the query is received at the device and from the server based on the query.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suppressing hotwords are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to playback of an utterance. The actions further include providing the audio data as an input to a model (i) that is configured to determine whether a given audio data sample includes an audio watermark and (ii) that was trained using watermarked audio data samples that each include an audio watermark sample and non-watermarked audio data samples that do not each include an audio watermark sample. The actions further include receiving, from the model, data indicating whether the audio data includes the audio watermark. The actions further include, based on the data indicating whether the audio data includes the audio watermark, determining to continue or cease processing of the audio data.

In some implementations, authentication tokens corresponding to known users of a device are stored on the device. An utterance from a speaker is received. The utterance is classified as spoken by a particular known user of the known users. A query that includes a representation of the utterance and an indication of the particular known user as the speaker is provided using the authentication token of the particular known user.

Growing community of inventors

Sunnyvale, CA, United States of America

Taral Pradeep Joglekar