2023å¹´4æ18æ¥ã«Microsoft Research Asiaã¨Microsoft Azureã®ã«ã¤ã»ã·ã§ã³æ°ãã®ç 究ãã¼ã ãæ¡æ£ã¢ãã«ã使ç¨ããå°å質ã®é³å£°åæã·ã¹ãã (TTS)ã§ãããNaturalSpeech 2ããçºè¡¨ãã¾ãããNaturalSpeech 2ã§ã¯æ°ç§ã®çãé³å£°ãµã³ãã«ãå©ç¨ããäºã§ã人ã®å£°ã ãã§ãªãæ声ã¾ã§ãå¿ å®ã«ã·ãã¥ã¬ã¼ããããã¨ãå¯è½ã«ãªã£ã¦ãã¾ãã [2304.09116] NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers https://doi.org/10.48550/arXiv.2304.09116 NaturalSpeech 2 https://speechresearch.github.io/na
{{#tags}}- {{label}}
{{/tags}}