EXPORTING MODULAR ENCODER FEATURES FOR STREAMING AND DELIBERATION ASR

• Main Authors: Botros, Rami Magdi Fahmi, Sainath, Tara N, Schalkwyk, Johan, Beaufays, Francoise, Prabhavalkar, Rohit Prakash, Chelba, Ciprian Ioan
• Format: Patent
• Language: English
• Published: 02.05.2024
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

A method includes obtaining a base encoder from a pre-trained model, and receiving training data comprising a sequence of acoustic frames characterizing an utterance paired with a ground-truth transcription of the utterance. At each of a plurality of output steps, the method includes: generating, by...