18627098. CONTRASTIVE LEARNING WITH ADVERSARIAL DATA FOR ROBUST SPEECH TRANSLATION (ZOOM VIDEO COMMUNICATIONS, INC.)
Contents
CONTRASTIVE LEARNING WITH ADVERSARIAL DATA FOR ROBUST SPEECH TRANSLATION
Organization Name
ZOOM VIDEO COMMUNICATIONS, INC.
Inventor(s)
Ravi Agrawal of San Francisco CA (US)
Shamil Chollampatt Muhammed Ashraf of Singapore (SG)
Sathish Reddy Indurthi of Cupertino CA (US)
Marco Turchi of Pergine Valsugana (IT)
CONTRASTIVE LEARNING WITH ADVERSARIAL DATA FOR ROBUST SPEECH TRANSLATION
This abstract first appeared for US patent application 18627098 titled 'CONTRASTIVE LEARNING WITH ADVERSARIAL DATA FOR ROBUST SPEECH TRANSLATION
Original Abstract Submitted
Systems and methods are disclosed for contrastive learning with adversarial data for robust speech translation. For example, a method may include inputting a speech signal to an automatic speech recognition model to obtain a transcript hypothesis including a first sequence of tokens, wherein the speech signal is associated with a golden transcript including a second sequence of tokens; inputting the first sequence of tokens to an encoder of a neural machine translation model to obtain a first sentence representation; inputting the second sequence of tokens to the encoder of the neural machine translation model to obtain a second sentence representation; determining a contrastive loss function based on the first sentence representation and the second sentence representation; and training the encoder of the neural machine translation model based on the contrastive loss function.
