Google Inc.

International Business Machines Corporation

Vijayaditya Peddinti

Alexander Houston Gruenstein

Michiel A U Bacchiani

Taral Pradeep Joglekar

Bhuvana Ramabhadran

Mateusz Golebiewski

Tara N Sainath

David Nahamoo

Vaibhava Goel

Rajeev Conrad Nongpiur

Etienne Marcheret

Brian E D Kingsbury

Andrew M Rosenberg

Petr Fousek

Shay Maymon

Michiel Bacchiani

Chan Woo Kim

Michiel AU Bacchiani

A method for instantaneous learning in text-to-speech (TTS) during dialog includes receiving a user pronunciation of a particular word present in a query spoken by a user. The method also includes receiving a TTS pronunciation of the same particular word that is present in a TTS input where the TTS pronunciation of the particular word is different than the user pronunciation of the particular word. The method also includes obtaining user pronunciation-related features and TTS pronunciation related features associated with the particular word. The method also includes generating a pronunciation decision selecting one of the user pronunciation or the TTS pronunciation of the particular word that is associated with a highest confidence. The method also include providing the TTS audio that includes a synthesized speech representation of the response to the query using the user pronunciation or the TTS pronunciation for the particular word.

Instantaneous learning in text-to-speech during dialog

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

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.

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.

An example method includes receiving, by a computing system, an indication of one or more audible sounds that are detected by a first sensing device, the one or more audible sounds originating from a user; determining, by the computing system and based at least in part on an indication of one or more signals detected by a second sensing device, a distance between the user and the second sensing device; determining, by the computing system and based at least in part on the indication of the one or more audible sounds, one or more acoustic features that are associated with the one or more audible sounds; and determining, by the computing system, and based at least in part on the one or more acoustic features and the distance between the user and the second sensing device, one or more words that correspond to the audible sounds.

Speech recognition using acoustic features in conjunction with distance information

Deep scattering spectral features are extracted from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal. The deep scattering spectral feature representation is input to a speech recognition engine. The acoustic input signal is decoded based on at least a portion of the deep scattering spectral feature representation input to a speech recognition engine.

Deep scattering spectrum in acoustic modeling for speech recognition

Growing community of inventors

San Jose, CA, United States of America

Vijayaditya Peddinti