Amazon Technologies, Inc. (20240428797). SPEECH PROCESSING
Contents
SPEECH PROCESSING
Organization Name
Inventor(s)
Liwei Cai of Cambridge MA (US)
Konstantine Arkoudas of North Bergen NJ (US)
Chengwei Su of Lexington MA (US)
Subendhu Rongali of New York NY (US)
SPEECH PROCESSING
This abstract first appeared for US patent application 20240428797 titled 'SPEECH PROCESSING
Original Abstract Submitted
techniques for performing spoken language understanding (slu) processing are described. an slu component may include an audio encoder configured to perform an audio-to-text processing task and an audio-to-nlu processing task. the slu component may also include a joint decoder configured to perform the audio-to-text processing task, the audio-to-nlu processing task and a text-to-nlu processing task. input audio data, representing a spoken input, is processed by the audio encoder and the joint decoder to determine nlu data corresponding to the spoken input.
