# The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment

arXiv: https://arxiv.org/abs/2004.00960 · HTML: https://mlsanity.com/paper/2004.00960/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 19 of 19)

- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Transformer Based Deliberation for Two-Pass Speech Recognition](https://mlsanity.com/paper/2101.11577/) (2021)
- [Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2203.14222/) (2022)
- [Conformer-based Hybrid ASR System for Switchboard Dataset](https://mlsanity.com/paper/2111.03442/) (2021)
- [Efficient Training of Neural Transducer for Speech Recognition](https://mlsanity.com/paper/2204.10586/) (2022)
- [Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction](https://mlsanity.com/paper/2306.09313/) (2023)
- [Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition](https://mlsanity.com/paper/2104.09106/) (2021)
- [Improving the Training Recipe for a Robust Conformer-based Hybrid Model](https://mlsanity.com/paper/2206.12955/) (2022)
- [On Architectures and Training for Raw Waveform Feature Extraction in ASR](https://mlsanity.com/paper/2104.04298/) (2021)
- [Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition](https://mlsanity.com/paper/2407.18930/) (2024)
- [AG-LSEC: Audio Grounded Lexical Speaker Error Correction](https://mlsanity.com/paper/2406.17266/) (2024)
- [The Impact of ASR on the Automatic Analysis of Linguistic Complexity and Sophistication in Spontaneous L2 Speech](https://mlsanity.com/paper/2104.08529/) (2021)
- [Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features](https://mlsanity.com/paper/2111.07130/) (2021)
- [Dynamic Acoustic Model Architecture Optimization in Training for ASR](https://mlsanity.com/paper/2506.13180/) (2025)
- [Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning Fusion](https://mlsanity.com/paper/2309.07164/) (2023)
- [Do we really need Self-Attention for Streaming Automatic Speech Recognition?](https://mlsanity.com/paper/2601.19960/) (2026)
- [SENS-ASR: Semantic Embedding injection in Neural-transducer for Streaming Automatic Speech Recognition](https://mlsanity.com/paper/2603.10005/) (2026)

## Abstract (arXiv)

We present a complete training pipeline to build a state-of-the-art hybrid HMM-based ASR system on the 2nd release of the TED-LIUM corpus. Data augmentation using SpecAugment is successfully applied to improve performance on top of our best SAT model using i-vectors. By investigating the effect of different maskings, we achieve improvements from SpecAugment on hybrid HMM models without increasing model size and training time. A subsequent sMBR training is applied to fine-tune the final acoustic model, and both LSTM and Transformer language models are trained and evaluated. Our best system achieves a 5.6% WER on the test set, which outperforms the previous state-of-the-art by 27% relative.