{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11521071","patent":{"patent_number":"US-11521071","title":"Utilizing deep recurrent neural networks with layer-wise attention for punctuation restoration","assignee":null,"inventors":[],"filing_date":"2019-05-14T00:00:00.000Z","publication_date":"2022-12-06T00:00:00.000Z","cpc_codes":["G06F","G06F","G06F","G06F","G06F","G06N","G06N","G06N","G06N","G06N","G06V","G06V"],"num_claims":20,"abstract":"The present disclosure relates to utilizing a deep recurrent neural network for accurately performing punctuation restoration. For example, the disclosed systems can provide a sequence of words to a punctuation restoration neural network having multiple bi-directional recurrent layers and one or more neural attention mechanisms. In one or more embodiments, the punctuation restoration neural network incorporates layer-wise attentions and/or multi-head attention. The disclosed systems can utilize the punctuation restoration neural network to generate probabilities for each word, indicating the likelihood that each possible punctuation mark is associated with that word. Based on these probabilities, the disclosed systems can generate a punctuated transcript that includes punctuation before the appropriate words."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Utilizing deep recurrent neural networks with layer-wise attention for punctuation restoration","description":"The present disclosure relates to utilizing a deep recurrent neural network for accurately performing punctuation restoration. For example, the disclosed systems can provide a sequence of words to a p","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11521071","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-11521071","citation_suggestion":"Patentable. \"Utilizing deep recurrent neural networks with layer-wise attention for punctuation restoration\" (US-11521071). https://patentable.app/patents/US-11521071","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11521071","json":"https://patentable.app/api/llm-context/US-11521071","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T01:36:37.042Z"}