# CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition

arXiv: https://arxiv.org/abs/2007.09127 · HTML: https://mlsanity.com/paper/2007.09127/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 30 of 76)

- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [YODAS: Youtube-Oriented Dataset for Audio and Speech](https://mlsanity.com/paper/2406.00899/) (2024)
- [Improving Gloss-free Sign Language Translation by Reducing Representation Density](https://mlsanity.com/paper/2405.14312/) (2024)
- [OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning](https://mlsanity.com/paper/2506.00338/) (2025)
- [Phone-to-audio alignment without text: A Semi-supervised Approach](https://mlsanity.com/paper/2110.03876/) (2021)
- [End-to-End Simultaneous Speech Translation with Differentiable Segmentation](https://mlsanity.com/paper/2305.16093/) (2023)
- [A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars](https://mlsanity.com/paper/2401.04730/) (2024)
- [ZIPA: A family of efficient models for multilingual phone recognition](https://mlsanity.com/paper/2505.23170/) (2025)
- [Improving ASR Contextual Biasing with Guided Attention](https://mlsanity.com/paper/2401.08835/) (2024)
- [Cross-modality Data Augmentation for End-to-End Sign Language Translation](https://mlsanity.com/paper/2305.11096/) (2023)
- [Towards Zero-Shot Code-Switched Speech Recognition](https://mlsanity.com/paper/2211.01458/) (2022)
- [Towards Hierarchical Spoken Language Dysfluency Modeling](https://mlsanity.com/paper/2401.10015/) (2024)
- [The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language](https://mlsanity.com/paper/2311.08323/) (2023)
- [Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence tasks](https://mlsanity.com/paper/2210.07499/) (2022)
- [Decoder-only Architecture for Streaming End-to-end Speech Recognition](https://mlsanity.com/paper/2406.16107/) (2024)
- [Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?](https://mlsanity.com/paper/2410.24019/) (2024)
- [Less Peaky and More Accurate CTC Forced Alignment by Label Priors](https://mlsanity.com/paper/2406.02560/) (2024)
- [Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model](https://mlsanity.com/paper/2301.12343/) (2023)
- [Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching](https://mlsanity.com/paper/2104.07491/) (2021)
- [MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research](https://mlsanity.com/paper/2406.18301/) (2024)
- [Contrastive Learning for Task-Independent SpeechLLM-Pretraining](https://mlsanity.com/paper/2412.15712/) (2024)
- [Direct Speech Translation for Automatic Subtitling](https://mlsanity.com/paper/2209.13192/) (2022)
- [4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders](https://mlsanity.com/paper/2212.10818/) (2022)
- [Advancing Test-Time Adaptation in Wild Acoustic Test Settings](https://mlsanity.com/paper/2310.09505/) (2023)
- [SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2401.09759/) (2024)
- [Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter](https://mlsanity.com/paper/2406.07096/) (2024)
- [AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation](https://mlsanity.com/paper/2504.20629/) (2025)
- [Whisper Has an Internal Word Aligner](https://mlsanity.com/paper/2509.09987/) (2025)
- [Streaming Joint Speech Recognition and Disfluency Detection](https://mlsanity.com/paper/2211.08726/) (2022)

## Abstract (arXiv)

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance. In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over 1700h of speech data. For data preparation, we propose a two-stage approach that uses an ASR model pre-trained with Connectionist Temporal Classification (CTC) to boot-strap more training data from unsegmented or unlabeled training data. Utterances are then extracted from label probabilities obtained from the network trained with CTC to determine segment alignments. With this training data, we trained a hybrid CTC/attention Transformer model that achieves 12.8% WER on the Tuda-DE test set, surpassing the previous baseline of 14.4% of conventional hybrid DNN/HMM ASR.