Features are disclosed for detecting words in audio using environmental information and/or
contextual information in addition to acoustic features associated with the words to be …

Methods, systems, and apparatus, including computer programs encoded on computer
storage media, for training a deep neural network. One of the methods for training a deep …

Systems and methods are disclosed for customizing a neural network for a custom dataset,
when the neural network has been trained on data from a general dataset. The neural …

Graves et al.“Speech Recognition with Deep Recurrent Neural Networks,” arXiv Preprint
arXiv 1303. 5778v1, Mar. 22, 2013, 5 pages.“Artificial neural network,” From Wikipedia, the …

(57) ABSTRACT A method of transfer learning includes receiving second data and
generating, via a first network, second labels for the second data. In one configuration, the …

Techniques related to a method and system of audio false keyphrase rejection using
speaker recognition are described herein. Such techniques use speaker recognition of a …

An approach to keyword spotting makes use of acoustic parameters that are trained on a
keyword spotting task as well as on a second speech recognition task, for example, a large …

Methods, systems, and apparatus for performing speech recognition. In some
implementations, acoustic data representing an utterance is obtained. The acoustic data …

Methods, systems, and apparatus, including computer pro grams encoded on a computer
storage medium, for training acoustic models and using the trained acoustic models. A …

Features are disclosed for detecting words in audio using contextual information in addition
to automatic speech recognition results. A detection model can be generated and used to …