# An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription

arXiv: https://arxiv.org/abs/1909.12208 · HTML: https://mlsanity.com/paper/1909.12208/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [Self-Supervised Learning for Speech Enhancement through Synthesis](https://mlsanity.com/paper/2211.02542/) (2022)
- [A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement](https://mlsanity.com/paper/2206.11000/) (2022)
- [Speech Enhancement for Wake-Up-Word detection in Voice Assistants](https://mlsanity.com/paper/2101.12732/) (2021)
- [BEA-Base: A Benchmark for ASR of Spontaneous Hungarian](https://mlsanity.com/paper/2202.00601/) (2022)
- [Code-Switched Urdu ASR for Noisy Telephonic Environment using Data Centric Approach with Hybrid HMM and CNN-TDNN](https://mlsanity.com/paper/2307.12759/) (2023)
- [Convoifilter: A case study of doing cocktail party speech recognition](https://mlsanity.com/paper/2308.11380/) (2023)
- [Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance](https://mlsanity.com/paper/2408.06264/) (2024)

## Abstract (arXiv)

Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate whether enhancement should also be carried out on the ASR training data. In an extensive experimental evaluation on the acoustically very challenging CHiME-5 dinner party data we show that: (i) cleaning up the training data can lead to substantial error rate reductions, and (ii) enhancement in training is advisable as long as enhancement in test is at least as strong as in training. This approach stands in contrast and delivers larger gains than the common strategy reported in the literature to augment the training database with additional artificially degraded speech. Together with an acoustic model topology consisting of initial CNN layers followed by factorized TDNN layers we achieve with 41.6% and 43.2% WER on the DEV and EVAL test sets, respectively, a new single-system state-of-the-art result on the CHiME-5 data. This is a 8% relative improvement compared to the best word error rate published so far for a speech recognizer without system combination.