# Open Source Automatic Speech Recognition for German

arXiv: https://arxiv.org/abs/1807.10311 · HTML: https://mlsanity.com/paper/1807.10311/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 8 of 8)

- [Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages](https://mlsanity.com/paper/2506.17459/) (2025)
- [Automated Evaluation of Standardized Dementia Screening Tests](https://mlsanity.com/paper/2206.06208/) (2022)
- [Using Kaldi for Automatic Speech Recognition of Conversational Austrian German](https://mlsanity.com/paper/2301.06475/) (2023)
- [ASR in German: A Detailed Error Analysis](https://mlsanity.com/paper/2204.05617/) (2022)
- [RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain](https://mlsanity.com/paper/2306.04054/) (2023)
- [Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers](https://mlsanity.com/paper/2102.05588/) (2021)
- [Detecting Emotion Carriers by Combining Acoustic and Lexical Representations](https://mlsanity.com/paper/2112.06603/) (2021)
- [Nonwords Pronunciation Classification in Language Development Tests for Preschool Children](https://mlsanity.com/paper/2206.08058/) (2022)

## Abstract (arXiv)

High quality Automatic Speech Recognition (ASR) is a prerequisite for speech-based applications and research. While state-of-the-art ASR software is freely available, the language dependent acoustic models are lacking for languages other than English, due to the limited amount of freely available training data. We train acoustic models for German with Kaldi on two datasets, which are both distributed under a Creative Commons license. The resulting model is freely redistributable, lowering the cost of entry for German ASR. The models are trained on a total of 412 hours of German read speech data and we achieve a relative word error reduction of 26% by adding data from the Spoken Wikipedia Corpus to the previously best freely available German acoustic model recipe and dataset. Our best model achieves a word error rate of 14.38 on the Tuda-De test set. Due to the large amount of speakers and the diversity of topics included in the training data, our model is robust against speaker variation and topic shift.