{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-10475484","patent":{"patent_number":"US-10475484","title":"Method and device for processing speech based on artificial intelligence","assignee":null,"inventors":[],"filing_date":"2017-06-30T00:00:00.000Z","publication_date":"2019-11-12T00:00:00.000Z","cpc_codes":["G11B","G10L","G10L","G10L","G11B"],"num_claims":17,"abstract":"The present disclosure discloses a method including: performing a silence detection on a speech to be decoded; cutting the speech to be decoded off to obtain a target speech if detecting that the speech to be detected is a silent speech; resetting tail features of the target speech with preset tail features of silent frames; and performing a CTC decoding process on the target speech reset. In embodiments, when a large number of blank frames are carried in the speech to be decoded, the speech to be decoded is cut off, and the tail features of the target speech is placed with the tail features of the silent frames such that there may be one CTC peak when the CTC decoding process is performed on the tail features of the target speech. Therefore, a last word of text content may be displayed rapidly on a screen."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Method and device for processing speech based on artificial intelligence","description":"The present disclosure discloses a method including: performing a silence detection on a speech to be decoded; cutting the speech to be decoded off to obtain a target speech if detecting that the spee","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-10475484","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-10475484","citation_suggestion":"Patentable. \"Method and device for processing speech based on artificial intelligence\" (US-10475484). https://patentable.app/patents/US-10475484","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-10475484","json":"https://patentable.app/api/llm-context/US-10475484","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-30T13:42:27.845Z"}