{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-10510004","patent":{"patent_number":"US-10510004","title":"Very deep convolutional neural networks for end-to-end speech recognition","assignee":null,"inventors":[],"filing_date":"2019-04-10T00:00:00.000Z","publication_date":"2019-12-17T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G10L","G10L","G10L"],"num_claims":10,"abstract":"A speech recognition neural network system includes an encoder neural network and a decoder neural network. The encoder neural network generates an encoded sequence from an input acoustic sequence that represents an utterance. The input acoustic sequence includes a respective acoustic feature representation at each of a plurality of input time steps, the encoded sequence includes a respective encoded representation at each of a plurality of time reduced time steps, and the number of time reduced time steps is less than the number of input time steps. The encoder neural network includes a time reduction subnetwork, a convolutional LSTM subnetwork, and a network in network subnetwork. The decoder neural network receives the encoded sequence and processes the encoded sequence to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Very deep convolutional neural networks for end-to-end speech recognition","description":"A speech recognition neural network system includes an encoder neural network and a decoder neural network. The encoder neural network generates an encoded sequence from an input acoustic sequence tha","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-10510004","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-10510004","citation_suggestion":"Patentable. \"Very deep convolutional neural networks for end-to-end speech recognition\" (US-10510004). https://patentable.app/patents/US-10510004","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-10510004","json":"https://patentable.app/api/llm-context/US-10510004","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T05:38:49.894Z"}