# Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription

arXiv: https://arxiv.org/abs/2004.10799 · HTML: https://mlsanity.com/paper/2004.10799/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 5 of 5)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors](https://mlsanity.com/paper/2310.16609/) (2023)
- [Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition](https://mlsanity.com/paper/2103.07186/) (2021)
- [Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments](https://mlsanity.com/paper/2207.07273/) (2022)

## Abstract (arXiv)

While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult cases, some end-to-end approaches show performance close to the hybrid baseline. To demonstrate this, we use the CHiME-6 Challenge data as an example of challenging environments and noisy conditions of everyday speech. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. We also provide a comparison of acoustic features and speech enhancements. Besides, we evaluate the effectiveness of neural network language models for hypothesis re-scoring in low-resource conditions. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline. With the Guided Source Separation based training data augmentation, this approach outperforms the hybrid baseline system by 2.7% WER abs. and the end-to-end system best known before by 25.7% WER abs.