slprl/StressPresso
收藏Hugging Face2025-11-11 更新2026-01-03 收录
下载链接:
https://hf-mirror.com/datasets/slprl/StressPresso
下载链接
链接失效反馈官方服务:
资源简介:
---
language:
- en
license: cc-by-nc-4.0
task_categories:
- question-answering
- automatic-speech-recognition
- audio-classification
- audio-text-to-text
dataset_info:
features:
- name: transcription
dtype: string
- name: intonation
dtype: string
- name: description
dtype: string
- name: possible_answers
sequence: string
- name: label
dtype: int64
- name: audio_lm_prompt
dtype: string
- name: audio
struct:
- name: array
sequence: float64
- name: path
dtype: string
- name: sampling_rate
dtype: int64
- name: stress_pattern
struct:
- name: binary
sequence: int64
- name: indices
sequence: int64
- name: words
sequence: string
- name: metadata
struct:
- name: audio_path
dtype: string
- name: gender
dtype: string
- name: speaker_id
dtype: string
- name: interpretation_id
dtype: string
- name: transcription_id
dtype: string
splits:
- name: test
num_bytes: 216570205
num_examples: 202
download_size: 135868258
dataset_size: 216570205
tags:
- speech
- stress
- intonation
- audio-reasoning
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
pretty_name: StressPresso
---
# StressPresso Evaluation Dataset
This dataset is derived from the *Expresso* dataset as introduced in the paper
**[EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://arxiv.org/pdf/2308.05725)**.
For additional information on *Expresso*, see its [project page](https://speechbot.github.io/expresso/).
The *StressPresso* dataset supports the evaluation of models on **Sentence Stress Reasoning (SSR)** and **Sentence Stress Detection (SSD)** tasks, as introduced in our paper:
**[StressTest: Can YOUR Speech LM Handle the Stress?](https://huggingface.co/papers/2505.22765)**
💻 [Code Repository](https://github.com/slp-rl/StressTest) | 🤗 [Model: StresSLM](https://huggingface.co/slprl/StresSLM) | 🤗 [Stress-17k Dataset](https://huggingface.co/datasets/slprl/Stress-17K-raw)
📃 [Paper](https://huggingface.co/papers/2505.22765) | 🌐 [Project Page](https://pages.cs.huji.ac.il/adiyoss-lab/stresstest/)
---
## 🗂️ Dataset Overview
The *StressPresso* dataset includes **202** evaluation samples (split: `test`) with the following features:
* `transcription_id`: Identifier for each transcription sample.
* `transcription`: The spoken text.
* `description`: Description of the interpretation of the stress pattern.
* `intonation`: The stressed version of the transcription.
* `interpretation_id`: Unique reference to the interpretation imposed by the stress pattern of the sentence.
* `audio`: Audio data at 48kHz sampling rate.
* `metadata`: Structured metadata including:
* `gender`: Speaker gender.
* `audio_path`: Expresso sample name.
* `speaker_id`: Expresso speaker id.
* `possible_answers`: List of possible interpretations for SSR.
* `label`: Ground truth label for SSR.
* `stress_pattern`: Structured stress annotation including:
* `binary`: Sequence of 0/1 labels marking stressed words.
* `indices`: Stressed word positions in the transcription.
* `words`: The actual stressed words.
* `audio_lm_prompt`: The prompt used for SSR.
---
## Evaluate YOUR model
This dataset is designed for evaluating models following the protocol and scripts in our [StressTest repository](https://github.com/slp-rl/StressTest).
To evaluate a model, refer to the instructions in the repository. For example:
```bash
python -m stresstest.evaluation.main \
--task ssr \
--model_to_evaluate stresslm
```
Replace `ssr` with `ssd` for stress detection, and use your model’s name with `--model_to_evaluate`.
---
## How to use
This dataset is formatted for usage with the HuggingFace Datasets library:
```python
from datasets import load_dataset
dataset = load_dataset("slprl/StressPresso")
```
---
## 📖 Citation
If you use this dataset in your work, please cite:
```bibtex
@misc{yosha2025stresstest,
title={StressTest: Can YOUR Speech LM Handle the Stress?},
author={Iddo Yosha and Gallil Maimon and Yossi Adi},
year={2025},
eprint={2505.22765},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.22765},
}
```
language:
- 英语
许可证:CC BY-NC 4.0
任务类别:
- 问答
- 自动语音识别
- 音频分类
- 音频-文本-文本
数据集信息:
特征:
- 名称:transcription(转录文本),数据类型:字符串
- 名称:intonation(语调特征),数据类型:字符串
- 名称:description(描述文本),数据类型:字符串
- 名称:possible_answers(候选答案集),数据类型:字符串序列
- 名称:label(标签),数据类型:64位整数
- 名称:audio_lm_prompt(语音大语言模型提示文本),数据类型:字符串
- 名称:audio(音频数据),结构体:
- 名称:array(音频数组),数据类型:64位浮点数序列
- 名称:path(音频路径),数据类型:字符串
- 名称:sampling_rate(采样率),数据类型:64位整数
- 名称:stress_pattern(重音模式),结构体:
- 名称:binary(重音二进制标记),数据类型:64位整数序列
- 名称:indices(重音词索引),数据类型:64位整数序列
- 名称:words(重音词列表),数据类型:字符串序列
- 名称:metadata(元数据),结构体:
- 名称:audio_path(音频路径),数据类型:字符串
- 名称:gender(说话人性别),数据类型:字符串
- 名称:speaker_id(说话人ID),数据类型:字符串
- 名称:interpretation_id(解释ID),数据类型:字符串
- 名称:transcription_id(转录文本ID),数据类型:字符串
划分集:
- 名称:测试集(test),字节数:216570205,样本数:202
下载大小:135868258
数据集总大小:216570205
标签:
- 语音
- 重音
- 语调
- 音频推理
配置项:
- 配置名称:default(默认配置),数据文件:
- 划分集:测试集,路径:data/test-*
展示名称:StressPresso
# StressPresso 评估数据集
本数据集源自论文**[EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://arxiv.org/pdf/2308.05725)**中提出的Expresso数据集。
如需了解Expresso的更多信息,请访问其[项目主页](https://speechbot.github.io/expresso/)。
StressPresso数据集可用于评估模型在**语句重音推理(Sentence Stress Reasoning, SSR)**和**语句重音检测(Sentence Stress Detection, SSD)**任务上的性能,相关细节可参阅我们的论文:
**[StressTest: Can YOUR Speech LM Handle the Stress?](https://huggingface.co/papers/2505.22765)**
💻 [代码仓库](https://github.com/slp-rl/StressTest) | 🤗 [模型:StresSLM](https://huggingface.co/slprl/StresSLM) | 🤗 [Stress-17k 数据集](https://huggingface.co/datasets/slprl/Stress-17K-raw)
📃 [论文](https://huggingface.co/papers/2505.22765) | 🌐 [项目主页](https://pages.cs.huji.ac.il/adiyoss-lab/stresstest/)
## 🗂️ 数据集概览
StressPresso数据集包含**202**个评估样本(划分集:`test`,即测试集),各特征说明如下:
* `transcription_id`:每条转录样本的唯一标识符。
* `transcription`:口语化文本内容。
* `description`:对语句重音模式的解释描述。
* `intonation`:带有目标重音的转录文本版本。
* `interpretation_id`:指向语句重音模式所对应解释的唯一引用标识。
* `audio`:采样率为48kHz的音频数据。
* `metadata`:结构化元数据,包含:
* `gender`:说话人性别。
* `audio_path`:Expresso数据集样本名称。
* `speaker_id`:Expresso数据集说话人ID。
* `possible_answers`:语句重音推理任务的候选解释列表。
* `label`:语句重音推理任务的真实标签。
* `stress_pattern`:结构化重音标注信息,包含:
* `binary`:标记重音词的0/1标签序列。
* `indices`:转录文本中重音词的位置索引。
* `words`:实际的重音词列表。
* `audio_lm_prompt`:用于语句重音推理任务的提示文本。
## 评估你的模型
本数据集的设计遵循我们[StressTest代码仓库](https://github.com/slp-rl/StressTest)中的评估协议与脚本。
如需评估模型,请参考仓库内的说明文档。示例如下:
bash
python -m stresstest.evaluation.main
--task ssr
--model_to_evaluate stresslm
若需执行重音检测任务,只需将`ssr`替换为`ssd`,并通过`--model_to_evaluate`参数指定待评估模型的名称。
## 使用方法
本数据集适配HuggingFace Datasets库进行加载,示例代码如下:
python
from datasets import load_dataset
dataset = load_dataset("slprl/StressPresso")
## 📖 引用说明
若您在研究中使用本数据集,请引用以下文献:
bibtex
@misc{yosha2025stresstest,
title={"StressTest: Can YOUR Speech LM Handle the Stress?"},
author={Iddo Yosha and Gallil Maimon and Yossi Adi},
year={2025},
eprint={2505.22765},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.22765},
}
提供机构:
slprl


