German dataset

The German dataset is a benchmark used to evaluate automatic speech recognition (ASR) systems, particularly in the context of speaker adaptation for dysarthric speech.

Papers using German dataset (11)

Word stress in self-supervised speech models: A cross-linguistic comparison2025 · 2 citesREINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation2025 · 1 citesLLM-based phoneme-to-grapheme for phoneme-based speech recognition2025 · 1 citesLanguage Barriers: Evaluating Cross-Lingual Performance of CNN and Transformer Architectures for Speech Quality Estimation2025 · 1 citesUnsupervised Cross-Lingual Part-of-Speech Tagging with Monolingual Corpora Only2026Evaluating Standard and Dialectal Frisian ASR: Multilingual Fine-tuning and Language Identification for Improved Low-resource Performance2025Analysis of Voice Conversion and Code-Switching Synthesis Using VQ-VAE2022 · 1 citesSpeaker adaptation for Wav2vec2 based dysarthric ASR2022Guided contrastive self-supervised pre-training for automatic speech recognition2022Efficient Utilization of Large Pre-Trained Models for Low Resource ASR2022Zero Resource Cross-Lingual Part Of Speech Tagging2024