{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-9842610","patent":{"patent_number":"US-9842610","title":"Training deep neural network for acoustic modeling in speech recognition","assignee":null,"inventors":[],"filing_date":"2015-06-26T00:00:00.000Z","publication_date":"2017-12-12T00:00:00.000Z","cpc_codes":["G10L","G10L"],"num_claims":15,"abstract":"A method is provided for training a Deep Neural Network (DNN) for acoustic modeling in speech recognition. The method includes reading central frames and side frames as input frames from a memory. The side frames are preceding side frames preceding the central frames and/or succeeding side frames succeeding the central frames. The method further includes executing pre-training for only the central frames or both the central frames and the side frames and fine-tuning for the central frames and the side frames so as to emphasize connections between acoustic features in the central frames and units of the bottom layer in hidden layer of the DNN."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Training deep neural network for acoustic modeling in speech recognition","description":"A method is provided for training a Deep Neural Network (DNN) for acoustic modeling in speech recognition. The method includes reading central frames and side frames as input frames from a memory. The","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-9842610","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-9842610","citation_suggestion":"Patentable. \"Training deep neural network for acoustic modeling in speech recognition\" (US-9842610). https://patentable.app/patents/US-9842610","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-9842610","json":"https://patentable.app/api/llm-context/US-9842610","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-06-06T07:27:21.597Z"}