# Advancing STT for Low-Resource Real-World Speech

arXiv: https://arxiv.org/abs/2506.08836 · HTML: https://mlsanity.com/paper/2506.08836/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German](https://mlsanity.com/paper/2103.11401/) (2021)
- [SDS-200: A Swiss German Speech to Standard German Text Corpus](https://mlsanity.com/paper/2205.09501/) (2022)
- [STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions](https://mlsanity.com/paper/2305.18855/) (2023)
- [Multilingual DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts](https://mlsanity.com/paper/2311.01070/) (2023)
- [Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text Corpus](https://mlsanity.com/paper/2010.02810/) (2020)
- [Learn and Don't Forget: Adding a New Language to ASR Foundation Models](https://mlsanity.com/paper/2407.06800/) (2024)
- [Adapting an ASR Foundation Model for Spoken Language Assessment](https://mlsanity.com/paper/2307.09378/) (2023)
- [Fine-tuning Whisper on Low-Resource Languages for Real-World Applications](https://mlsanity.com/paper/2412.15726/) (2024)
- [Spaiche: Extending State-of-the-Art ASR Models to Swiss German Dialects](https://mlsanity.com/paper/2304.11075/) (2023)
- [Does Whisper understand Swiss German? An automatic, qualitative, and human evaluation](https://mlsanity.com/paper/2404.19310/) (2024)
- [Swiss German Speech to Text system evaluation](https://mlsanity.com/paper/2207.00412/) (2022)
- [Dialect Transfer for Swiss German Speech Translation](https://mlsanity.com/paper/2310.09088/) (2023)
- [Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition](https://mlsanity.com/paper/2409.16954/) (2024)
- [Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages](https://mlsanity.com/paper/2411.04573/) (2024)
- [SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition](https://mlsanity.com/paper/2409.10429/) (2024)
- [Using fine-tuning and min lookahead beam search to improve Whisper](https://mlsanity.com/paper/2309.10299/) (2023)

## Built on by (most cited first, 1 of 1)

- [Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)](https://mlsanity.com/paper/2606.07608/) (2026)

## Abstract (arXiv)

Swiss German is a low-resource language represented by diverse dialects that differ significantly from Standard German and from each other, lacking a standardized written form. As a result, transcribing Swiss German involves translating into Standard German. Existing datasets have been collected in controlled environments, yielding effective speech-to-text (STT) models, but these models struggle with spontaneous conversational speech. This paper, therefore, introduces the new SRB-300 dataset, a 300-hour annotated speech corpus featuring real-world long-audio recordings from 39 Swiss German radio and TV stations. It captures spontaneous speech across all major Swiss dialects recorded in various realistic environments and overcomes the limitation of prior sentence-level corpora. We fine-tuned multiple OpenAI Whisper models on the SRB-300 dataset, achieving notable enhancements over previous zero-shot performance metrics. Improvements in word error rate (WER) ranged from 19% to 33%, while BLEU scores increased between 8% and 40%. The best fine-tuned model, large-v3, achieved a WER of 17.1% and a BLEU score of 74.8. This advancement is crucial for developing effective and robust STT systems for Swiss German and other low-resource languages in real-world contexts.