D149_Multi_style_Average_Tone_Speech_Synthesis_Corpus_Customer_S

40人多风格平均音色合成库，由专业声优采集，24种风格分别为北京话、电影解说、华妃、纪录片解说、美食解说、小说解说、中青年磁性男、怼人杜飞、孙悟空、温暖男声、TVB 女声、广西表哥、林黛玉、哪吒、如来、申公豹、太乙真人、温柔桃子、徐志胜、周杰伦、河南大叔、气泡音、容嬷嬷、天津小哥、天真幼童、正气男声、咆哮哥、四郎、海夜叉、导购女声、海绵宝宝、唐僧、鸭子嗓、阳光男声、东厂公公、新闻女声、乖巧童声、软糯童声、有声书男、有声书女。A 40-speaker multi-style average timbre synthesis dataset collected by professional voiceover artists. The included timbre styles are: Beijing dialect, movie commentary, Imperial Concubine Hua, documentary commentary, food commentary, novel commentary, middle-aged and young male with magnetic voice, snarky Du Fei, Monkey King, warm male voice, TVB-style female voice, Guangxi cousin, Lin Daiyu, Nezha, Tathagata Buddha, Shen Gongbao, Taiyi Zhenren, Gentle Taozi, Xu Zhisheng, Jay Chou, Henan uncle, breathy voice, Rong Momo, Tianjin guy, naive young child voice, upright righteous male voice, roaring persona, Fourth Master, Sea Yaksha, shopping guide female voice, SpongeBob SquarePants, Tang Sanzang, duck-like voice, sunny male voice, Eastern Depot eunuch, news broadcast female voice, well-behaved child voice, soft velvety child voice, audio book male voice, audio book female voice.

搜集汇总

背景与挑战

背景概述

该数据集是一个多风格平均音色合成库，由40位专业声优在专业录音棚环境下录制，包含40种不同风格（如北京话、电影解说、华妃等），音频格式为48kHz、24bit、wav单声道，适用于中文普通话的语音合成任务。