{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11990117","patent":{"patent_number":"US-11990117","title":"Using speech recognition to improve cross-language speech synthesis","assignee":null,"inventors":[],"filing_date":"2021-10-20T00:00:00.000Z","publication_date":"2024-05-21T00:00:00.000Z","cpc_codes":["G10L","G10L","G06N","G06N","G06N","G06N","G06N","G06N","G06N","G10L","G10L","G10L","G10L","G10L","G10L","G10L"],"num_claims":20,"abstract":"A method for training a speech recognition model includes obtaining a multilingual text-to-speech (TTS) model. The method also includes generating a native synthesized speech representation for an input text sequence in a first language that is conditioned on speaker characteristics of a native speaker of the first language. The method also includes generating a cross-lingual synthesized speech representation for the input text sequence in the first language that is conditioned on speaker characteristics of a native speaker of a different second language. The method also includes generating a first speech recognition result for the native synthesized speech representation and a second speech recognition result for the cross-lingual synthesized speech representation. The method also includes determining a consistent loss term based on the first speech recognition result and the second speech recognition result and updating parameters of the speech recognition model based on the consistent loss term."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Using speech recognition to improve cross-language speech synthesis","description":"A method for training a speech recognition model includes obtaining a multilingual text-to-speech (TTS) model. The method also includes generating a native synthesized speech representation for an inp","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11990117","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-11990117","citation_suggestion":"Patentable. \"Using speech recognition to improve cross-language speech synthesis\" (US-11990117). https://patentable.app/patents/US-11990117","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11990117","json":"https://patentable.app/api/llm-context/US-11990117","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T03:24:05.145Z"}