Table · dataset · 2026
SpeechArenaBench
Listed in Hugging Face Datasets
SpeechArenaBench SpeechArenaBench is a large-scale human-preference dataset for evaluating multilingual Text-to-Speech (TTS) systems across 10 Indian languages.
Description
It accompanies the paper "Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages" (accepted to Interspeech 2026), and contains the full benchmark sentences, generated audio, and crowd-sourced pairwise preference judgments collected from native raters.
The… See the full description on the dataset page: huggingface.co/datasets/ai4bharat/SpeechArenaBench.
Links
Get the data
- Hugging Face dataset page huggingface.co/datasets/ai4bharat/SpeechArenaBench ↗
Gated (auto) - request access on the dataset page
landing page · request access · from Hugging Face
Where it is published
- DOI doi.org/10.57967/hf/9219 ↗
DOI / persistent id · from Hugging Face
Documentation and papers
- arXiv:2604.21481 arxiv.org/abs/2604.21481 ↗
publication · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/ai4bharat/SpeechArenaBench ↗
metadata API · from Hugging Face
Topics
- From keywords
- Audio · Computer Science & AI
- Inferred from text
- Artificial intelligence 71%
Provenance · 1 source records, 12 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | ai4bharat/SpeechArenaBench | 14 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].anzsrc:group:4602 | enrichment · Hugging Face | taxonomy-embedding@1.1.0 | title+keywords+description (71%) |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].hf_modality:audio | source · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].hf_modality:text | source · Hugging Face | connector:huggingface@1.0.0 | |
| concepts[modality].local:modality:audio | mapping · Hugging Face | vocabulary-mapper@1.0.0 | keywords['audio'] |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| license | source · Hugging Face | connector:huggingface@1.0.0 | /tags[license:*] |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |