Open Source Automatic Speech Recognition for German

Benjamin Milde, Arne Köhn
7/26/2018
cs.CL

Official code: uhh-lt/kaldi-tuda-de (177 stars, Apache-2.0, last commit 2023-08-09).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

uhh-lt/kaldi-tuda-deOfficial100%
Apache-2.0

Scripts for training general-purpose large vocabulary German acoustic models for ASR with Kaldi.

17735Shell, PythonJan 19, 20153 years agoApache-2.0

Similar Papers

ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks

87% match2022

Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data

86% match1 repo10.0k2023

Textually Pretrained Speech Language Models

86% match1 repo222023

LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data

85% match2023

Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models

84% match1 repo92020

Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models

84% match2026

Cite this paper

@article{milde2018open,
  title  = {Open Source Automatic Speech Recognition for German},
  author = {Benjamin Milde and Arne Köhn},
  year   = {2018},
  eprint = {1807.10311},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1807.10311}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1807.10311.svg)](https://codeofpaper.com/paper/1807.10311)

Discussion