{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11475874","patent":{"patent_number":"US-11475874","title":"Generating diverse and natural text-to-speech samples","assignee":null,"inventors":[],"filing_date":"2021-01-29T00:00:00.000Z","publication_date":"2022-10-18T00:00:00.000Z","cpc_codes":["G10L","G10L","G06N","G10L","G10L","G10L","G10L","G10L","G10L","G10L"],"num_claims":20,"abstract":"A method of generating diverse and natural text-to-speech (TTS) samples includes receiving a text and generating a speech sample based on the text using a TTS model. A training process trains the TTS model to generate the speech sample by receiving training samples. Each training sample includes a spectrogram and a training text corresponding to the spectrogram. For each training sample, the training process identifies speech units associated with the training text. For each speech unit, the training process generates a speech embedding, aligns the speech embedding with a portion of the spectrogram, extracts a latent feature from the aligned portion of the spectrogram, and assigns a quantized embedding to the latent feature. The training process generates the speech sample by decoding a concatenation of the speech embeddings and a quantized embeddings for the speech units associated with the training text corresponding to the spectrogram."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Generating diverse and natural text-to-speech samples","description":"A method of generating diverse and natural text-to-speech (TTS) samples includes receiving a text and generating a speech sample based on the text using a TTS model. A training process trains the TTS ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11475874","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-11475874","citation_suggestion":"Patentable. \"Generating diverse and natural text-to-speech samples\" (US-11475874). https://patentable.app/patents/US-11475874","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11475874","json":"https://patentable.app/api/llm-context/US-11475874","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T06:59:46.701Z"}