Google Inc.

Min Ma

Pedro Jose Moreno Mengibar

Bhuvana Ramabhadran

Yu Zhang

Ruoming Pang

Arun Narayanan

Chung-Cheng Chiu

Wei Han

Ananya Misra

Brian E Roark

Liangliang Cao

Jesse Emond

Thibault Doutre

A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.

Streaming automatic speech recognition with non-streaming model distillation

Methods, systems, and apparatus, including computer programs stored on a computer-readable storage medium, for transliteration for speech recognition training and scoring. In some implementations, language examples are accessed, some of which include words in a first script and words in one or more other scripts. At least portions of some of the language examples are transliterated to the first script to generate a training data set. A language model is generated based on occurrences of the different sequences of words in the training data set in the first script. The language model is used to perform speech recognition for an utterance.

Transliteration for speech recognition training and scoring

Growing community of inventors

New York, NY, United States of America

Min Ma