S-DiverSe: Spanish Diverse Speech
Quick Answer
S-DiverSe is a new Spanish speech corpus featuring 3.2 hours of recordings from 22 speakers with neurological conditions.
Quick Take
S-DiverSe is a new Spanish speech corpus featuring 3.2 hours of recordings from 22 speakers with neurological conditions. It aims to enhance automatic speech recognition (ASR) for affected individuals, revealing that heuristic text post-processing outperforms fine-tuning for ASR adaptation in this domain.
Key Points
- Corpus includes 444 transcribed audio segments with metadata on speaker characteristics.
- Designed specifically for ASR evaluation of neurologically affected Spanish speech.
- Initial experiments show heuristic post-processing is more effective than fine-tuning.
- Highlights the need for dedicated benchmarks for in-the-wild Spanish speech.
- Accepted for presentation at Interspeech 2026.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Automatic speech recognition (ASR) has advanced remarkably for standard speech, yet speech affected by neurological conditions remains a challenge. We present S-DiverSe (Spanish Diverse Speech), a corpus of 3.2 hours of in-the-wild Spanish speech from 22 speakers with amyotrophic lateral sclerosis, Parkinson's disease, and stroke. The dataset contains 444 manually transcribed audio segments with metadata on speaker sex, disease type, and intelligibility. S-DiverSe is designed to support ASR evaluation and development for neurologically affected Spanish speech. We describe the dataset, analyze its composition, and report baseline ASR results alongside initial adaptation experiments. Our findings reveal that heuristic text post-processing is more robust than fine-tuning for out-of-domain neurological Spanish speech. This underscores the need for dedicated in-the-wild Spanish benchmarks.
| Comments: | Accepted in Interspeech 2026 |
| Subjects: | Computation and Language (cs.CL); Sound (cs.SD) |
| Cite as: | arXiv:2607.03207 [cs.CL] |
| (or arXiv:2607.03207v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03207 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fernando López PhD(c) [view email]
[v1]
Fri, 3 Jul 2026 11:23:43 UTC (59 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.