Google Inc.

Alexandru Ovidiu Dovlecel

Gleb Skobeltsyn

Zaheed Sabur

Martin Baeuml

Tilke Mary Judd

Ardan Arac

Vladimir Vuskovic

Stephan Wenger

Zineb Ait Bahajji

Eduardo Jodas Samper

Jyrki Antero Alakuijala

Ágoston Weisz

Peter W Dickman

Abraham Moolenaar

Marvin Chow

Evgeny A Cherepanov

Lukas Lopatovsky

Justas Klimavicius

Yihui Ma

Behshad Behzadi

Ignacio Lopez Moreno

Dmitry Osmakov

Carl-Anton Ingmarsson

Implementations set forth herein relate to speech recognition techniques for handling variations in speech among users (e.g. due to different accents) and processing features of user context in order to expand a number of speech recognition hypotheses when interpreting a spoken utterance from a user. In order to adapt to an accent of the user, terms common to multiple speech recognition hypotheses can be filtered out in order to identify inconsistent terms apparent in a group of hypotheses. Mappings between inconsistent terms can be stored for subsequent users as term correspondence data. In this way, supplemental speech recognition hypotheses can be generated and subject to probability-based scoring for identifying a speech recognition hypothesis that most correlates to a spoken utterance provided by a user. In some implementations, prior to scoring, hypotheses can be supplemented based on contextual data, such as on-screen content and/or application capabilities.

Speech recognition hypothesis generation according to previous occurrences of hypotheses terms and/or contextual data

Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Proactive incorporation of unsolicited content into human-to-computer dialogs

Techniques are disclosed that enable determining and/or utilizing a misrecognition of a spoken utterance, where the misrecognition is generated using an automatic speech recognition (ASR) model. Various implementations include determining a recognition based on the spoken utterance and a previous utterance spoken prior to the spoken utterance. Additionally or alternatively, implementations include personalizing an ASR engine for a user based on the spoken utterance and the previous utterance spoken prior to the spoken utterance (e.g., based on audio data capturing the previous utterance and a text representation of the spoken utterance).

Identification and utilization of misrecognitions in automatic speech recognition

Implementations include actions of obtaining a set of entities based on one or more terms of a query, obtaining one or more entities associated with each live event of a plurality of live events, identifying a live event that is responsive to the query based on comparing at least one entity in the set of entities to one or more entities associated with each live event of a plurality of live events, determining that an event search result corresponding to the live event is to be displayed in search results, and in response: providing the event search result for display, the event search result including information associated with the live event, the information including an indicator of an occurrence of the live event.

Surfacing live events in search results

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, receiving a search query from a user; determining that a voting user interface (VUI) is to be provided based on the search query, the VUI enabling the user to submit one or more votes in a vote-based campaign; receiving search results that are responsive to the search query; and transmitting instructions to display the search results and the VUI.

Supporting voting-based campaigns in search

Methods, including computer programs encoded on a computer storage medium, for collaborative language model biasing. In one aspect, a method includes: obtaining (i) one or more initial candidate transcriptions, and (ii) one or more terms that are associated with a context; selecting one or more of the terms that are associated with the context, and that (i) do not occur in the candidate transcriptions, and (ii) are indicated as phonetically similar to one or more terms that do occur in the initial candidate transcriptions; generating one or more additional candidate transcriptions based on the (i) initial candidate transcriptions, and (ii) the selected terms; and providing the one or more additional candidate transcriptions to an automated speech recognizer.

Contextual improvement of voice query recognition

Display panel or portion thereof with animated computer icon

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, determining that a voting user interface (VUI) is to be provided with search results, the VUI enabling a user to submit one or more votes in a voting-based campaign; receiving social content, the social content having been distributed using one or more social networking services; receiving search results that are responsive to a search query; and transmitting instructions to display the search results and the VUI, the VUI comprising the social content.

Social voting-based campaigns in search

Growing community of inventors

Zurich, Switzerland

Alexandru Ovidiu Dovlecel