ylacombe/expresso

Name: ylacombe/expresso
Creator: ylacombe
Published: 2024-04-30 16:49:14
License: 暂无描述

Hugging Face2024-04-30 更新2024-05-25 收录

下载链接：

https://hf-mirror.com/datasets/ylacombe/expresso

下载链接

链接失效反馈

官方服务：

资源简介：

--- dataset_info: config_name: read features: - name: audio dtype: audio - name: text dtype: string - name: speaker_id dtype: string - name: style dtype: string - name: id dtype: string splits: - name: train num_bytes: 5702432944.34 num_examples: 11615 download_size: 5761373569 dataset_size: 5702432944.34 configs: - config_name: read data_files: - split: train path: read/train-* license: cc-by-nc-4.0 language: - en pretty_name: The Expresso Dataset --- # The Expresso Dataset [[paper]](https://arxiv.org/abs/2308.05725) [[demo samples]](https://speechbot.github.io/expresso/) [[Original repository]](https://github.com/facebookresearch/textlesslib/tree/main/examples/expresso/dataset) ## Introduction The Expresso dataset is a high-quality (48kHz) expressive speech dataset that includes both expressively rendered read speech (8 styles, in mono wav format) and improvised dialogues (26 styles, in stereo wav format). The dataset includes 4 speakers (2 males, 2 females), and totals 40 hours (11h read, 30h improvised). The transcriptions of the read speech are also provided. You can listen to samples from the Expresso Dataset at [this website](https://speechbot.github.io/expresso/). ## Data Statistics Here are the statistics of Expresso’s expressive styles: ---------------------------------------------------------------- Style | Read (min) | Improvised (min) | total (hrs) ------------------|------------|------------------|------------- angry | - | 82 | 1.4 animal | - | 27 | 0.4 animal_directed | - | 32 | 0.5 awe | - | 92 | 1.5 bored | - | 92 | 1.5 calm | - | 93 | 1.6 child | - | 28 | 0.4 child_directed | - | 38 | 0.6 confused | 94 | 66 | 2.7 default | 133 | 158 | 4.9 desire | - | 92 | 1.5 disgusted | - | 118 | 2.0 enunciated | 116 | 62 | 3.0 fast | - | 98 | 1.6 fearful | - | 98 | 1.6 happy | 74 | 92 | 2.8 laughing | 94 | 103 | 3.3 narration | 21 | 76 | 1.6 non_verbal | - | 32 | 0.5 projected | - | 94 | 1.6 sad | 81 | 101 | 3.0 sarcastic | - | 106 | 1.8 singing* | - | 4 | .07 sleepy | - | 93 | 1.5 sympathetic | - | 100 | 1.7 whisper | 79 | 86 | 2.8 **Total** | **11.5h** | **34.4h** | **45.9h** ---------------------------------------------------------------- *singing is the only improvised style that is not in dialogue format. ## Audio Quality The audio was recorded in a professional recording studio with minimal background noise at 48kHz/24bit. The files for read speech and singing are in a mono wav format; and for the dialog section in stereo (one channel per actor), where the original flow of turn-taking is preserved. ### Read Speech The `read` config contains all the read speech and singing style. ## License The Expresso dataset is distributed under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/) license. ## Reference For more information, see the paper: [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://arxiv.org/abs/2308.05725), Tu Anh Nguyen*, Wei-Ning Hsu*, Antony D'Avirro*, Bowen Shi*, Itai Gat, Maryam Fazel-Zarani, Tal Remez, Jade Copet, Gabriel Synnaeve, Michael Hassid, Felix Kreuk, Yossi Adi⁺, Emmanuel Dupoux⁺, INTERSPEECH 2023.

数据集信息：配置名称：朗读（read）特征： - 名称：音频（audio），数据类型：音频 - 名称：文本（text），数据类型：字符串 - 名称：说话人ID（speaker_id），数据类型：字符串 - 名称：风格（style），数据类型：字符串 - 名称：ID（id），数据类型：字符串划分集： - 名称：训练集（train），字节数：5702432944.34，样本数：11615 下载大小：5761373569，数据集总大小：5702432944.34 配置项： - 配置名称：朗读（read），数据文件： - 划分集：训练集（train），路径：read/train-* 许可协议：CC BY-NC 4.0 语言：英语（en）规范名称：Expresso数据集 # Expresso数据集 [[论文]](https://arxiv.org/abs/2308.05725) [[演示样例]](https://speechbot.github.io/expresso/) [[原始仓库]](https://github.com/facebookresearch/textlesslib/tree/main/examples/expresso/dataset) ## 数据集简介 Expresso数据集是一款高质量（48kHz）的情感语音数据集，涵盖两类经情感渲染的语音数据：其一为朗读语音（共8种风格，采用单声道WAV格式存储），其二为即兴对话语音（共26种风格，采用立体声WAV格式存储）。该数据集包含4名说话人（2名男性、2名女性），总时长共计40小时，其中朗读语音11小时，即兴语音30小时，同时附带朗读语音的转写文本。您可通过[该网站](https://speechbot.github.io/expresso/)试听Expresso数据集的样例音频。 ## 数据统计信息以下为Expresso数据集各情感风格的统计数据： | 情感风格 | 朗读语音（分钟） | 即兴语音（分钟） | 总时长（小时） | |------------------|----------------|----------------|--------------| | 愤怒 | - | 82 | 1.4 | | 动物拟声 | - | 27 | 0.4 | | 定向动物语音 | - | 32 | 0.5 | | 敬畏 | - | 92 | 1.5 | | 无聊 | - | 92 | 1.5 | | 平静 | - | 93 | 1.6 | | 儿童语音 | - | 28 | 0.4 | | 定向儿童语音 | - | 38 | 0.6 | | 困惑 | 94 | 66 | 2.7 | | 标准语音 | 133 | 158 | 4.9 | | 渴望 | - | 92 | 1.5 | | 厌恶 | - | 118 | 2.0 | | 清晰发音 | 116 | 62 | 3.0 | | 快速 | - | 98 | 1.6 | | 恐惧 | - | 98 | 1.6 | | 开心 | 74 | 92 | 2.8 | | 大笑 | 94 | 103 | 3.3 | | 旁白 | 21 | 76 | 1.6 | | 非语音 | - | 32 | 0.5 | | 投射式语音 | - | 94 | 1.6 | | 悲伤 | 81 | 101 | 3.0 | | 讽刺 | - | 106 | 1.8 | | 歌唱* | - | 4 | 0.07 | | 困倦 | - | 93 | 1.5 | | 同情 | - | 100 | 1.7 | | 耳语 | 79 | 86 | 2.8 | | **总计** | **11.5小时** | **34.4小时** | **45.9小时** | *注：歌唱是唯一非对话格式的即兴风格语音。 ## 音频质量本数据集音频均于专业录音棚录制，背景噪音极低，采样率为48kHz、位深度24bit。朗读语音与歌唱风格语音采用单声道WAV格式存储；对话部分则采用立体声格式（每位说话人对应一个声道），完整保留了原始的轮次对话流程。 ### 朗读语音配置「read」配置包含全部朗读语音与歌唱风格的语音数据。 ## 许可协议 Expresso数据集采用[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/)许可协议进行分发。 ## 参考文献如需了解更多细节，请参阅论文：[EXPRESSO：离散式情感语音合成的基准测试与分析](https://arxiv.org/abs/2308.05725)，作者：Tu Anh Nguyen*、Wei-Ning Hsu*、Antony D'Avirro*、Bowen Shi*、Itai Gat、Maryam Fazel-Zarani、Tal Remez、Jade Copet、Gabriel Synnaeve、Michael Hassid、Felix Kreuk、Yossi Adi⁺、Emmanuel Dupoux⁺，发表于INTERSPEECH 2023。

提供机构：

ylacombe

原始信息汇总