Google Inc.

Yun-hsuan Sung

Brian Strope

Raymond C Kurzweil

Wangqing Yuan

Matthew Henderson

Francoise Beaufays

Tobias Kaufmann

Rami Al-Rfou'

Yonghui Wu

Hasim Sak

Timothy Youngjin Sohn

Balint Miklos

Xin Lei

Cyril Georges Luc Allauzen

Benjamin N Lee

Gregory R Bullock

Paul Roland Lambert

Jacqueline Amy Tsay

Xu Chen

Matthew Vincent Dierker

Rami Al-Rfou′

Jui-Ting Huang

Hui Lin

Gagan Bansal

Neil Smith

Noah Constant

Victor Anchidin

Tobias Bosch

Jan Van De Kerkhof

Rami Eid Sammouf Al-Rfou'

Ettore Randazzo

Do Kook Choe

Justin Tzi-jay Lu

Kaushik Roy

Yinan Wang

Amr Abdelfattah

Cole Austin Bevis

Katherine Anna Evans

Meihong Wang

László Lukacs

Bjarke Ebert

Heeyoung Lee

Wanqing Yuan

Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and/or indirectly); and/or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a 'semantic textual similarity' task for which the encoder model can be used.

Training encoder model and/or using trained encoder model to determine responsive action(s) for natural language input

Systems, methods, and computer readable media related to information retrieval. Some implementations are related to training and/or using a relevance model for information retrieval. The relevance model includes an input neural network model and a subsequent content neural network model. The input neural network model and the subsequent content neural network model can be separate, but trained and/or used cooperatively. The input neural network model and the subsequent content neural network model can be 'separate' in that separate inputs are applied to the neural network models, and each of the neural network models is used to generate its own feature vector based on its applied input. A comparison of the feature vectors generated based on the separate network models can then be performed, where the comparison indicates relevance of the input applied to the input neural network model to the separate input applied to the subsequent content neural network model.

Cooperatively training and/or using separate input and subsequent content neural networks for information retrieval

A computing system is described that includes user interface components configured to receive typed user input; and one or more processors. The one or more processors are configured to: receive, by a computing system and at a first time, a first portion of text typed by a user in an electronic message being edited; predict, based on the first portion of text, a first candidate portion of text to follow the first portion of text; output, for display, the predicted first candidate portion of text for optional selection to append to the first portion of text; determine, at a second time that is after the first time, that the electronic message is directed to a sensitive topic; and responsive to determining that the electronic message is directed to a sensitive topic, refrain from outputting subsequent candidate portions of text for optional selection to append to text in the electronic message.

Selective text prediction for electronic messaging

Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Cooperatively training and/or using separate input and response neural network models for determining response(s) for electronic communications

A system may use a machine-learned model to determine whether to classify a sequence of one or more words within a first document that is being edited as a candidate hyperlink based at least in part on context associated with the first document. In response to classifying the sequence of one or more words as the candidate hyperlink, the system may use the machine-learned model and based at least in part on the sequence of one or more words and the context to determine one or more candidate document to be hyperlinked from the sequence of one or more words. In response to receiving an indication of a second document being selected out of the one or more candidate documents, the system may modify the first document to associate the sequence of one or more words with a hyperlink to the second document.

Automatic hyperlinking of documents

An automatic speech recognition system and method are provided for written-domain language modeling. According to one implementation, a process includes accessing decomposed training data that results from applying rewrite grammar rules to original training data, the decomposed training data comprising (i) regular words from the original training data that have not been rewritten using the set of rewrite grammar rules, and (ii) decomposed segments that result from rewriting non-lexical entities from the original training data using the rewrite grammar rules, generating a restriction model that (i) maps language model paths for regular words to themselves, and (ii) restricts language model paths for decomposed segments for non-lexical entities, training a n-gram language model over the training data, composing the restriction model and the language model to obtain a restricted language model, and constructing a decoding network by composing a context dependency model and a pronunciation lexicon with the restricted language model.

Written-domain language modeling with decomposition

Speech recognition systems may perform the following operations: receiving audio at a computing device; identifying a language associated with the audio; recognizing the audio using recognition models for different versions of the language to produce recognition candidates for the audio, where the recognition candidates are associated with corresponding information; comparing the information of the recognition candidates to identify agreement between at least two of the recognition models; selecting a recognition candidate based on information of the recognition candidate and agreement between the at least two of the recognition models; and outputting data corresponding to the selected recognition candidate as a recognized version of the audio.

Recognizing different versions of a language

Speech recognition systems may perform the following operations: receiving audio; recognizing the audio using language models for different languages to produce recognition candidates for the audio, where the recognition candidates are associated with corresponding recognition scores; identifying a candidate language for the audio; selecting a recognition candidate based on the recognition scores and the candidate language; and outputting data corresponding to the selected recognition candidate as a recognized version of the audio.

Recognizing speech in multiple languages

A computer-implemented method for digital speech processing, including (1) receiving, at a server computer, digital speech data from a computing device, the digital speech data comprising data points sampled at respective time points; (2) computing, by the server computer, a tonal feature of the digital speech data, the tonal feature comprising information encoding fundamental frequencies at the respective time points; (3) computing, by the server computer, a logarithm of the tonal feature at the respective time points; and (4) processing, by the server computer, the logarithm of the tonal feature based on a characterization of the digital speech data at the respective time points.

Mobile speech recognition with explicit tone features

Growing community of inventors

Mountain View, CA, United States of America

Yun-hsuan Sung