US Patent Application 18234350. GENERATING STRUCTURED TEXT CONTENT USING SPEECH RECOGNITION MODELS simplified abstract
Contents
GENERATING STRUCTURED TEXT CONTENT USING SPEECH RECOGNITION MODELS
Organization Name
Inventor(s)
Christopher S. Co of Saratoga CA (US)
Navdeep Jaitly of Mountain View CA (US)
Lily Hao Yi Peng of Mountain View CA (US)
Katherine Irene Chou of Palo Alto CA (US)
Ananth Sankar of Palo Alto CA (US)
GENERATING STRUCTURED TEXT CONTENT USING SPEECH RECOGNITION MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18234350 titled 'GENERATING STRUCTURED TEXT CONTENT USING SPEECH RECOGNITION MODELS
Simplified Explanation
The patent application is about methods, systems, and apparatus for speech recognition.
- The method involves obtaining an input acoustic sequence that represents one or more utterances.
- The input acoustic sequence is processed using a speech recognition model to generate a transcription of the input sequence.
- The speech recognition model includes a domain-specific language model.
- The generated transcription is then used as input to a domain-specific predictive model.
- The domain-specific predictive model generates structured text content derived from the transcription of the input sequence.
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.