# Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora

arXiv: https://arxiv.org/abs/2109.11086 · HTML: https://mlsanity.com/paper/2109.11086/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 23 Sep 2021.

## Builds on (most cited first, 9 of 9)

- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Towards Learning a Universal Non-Semantic Representation of Speech](https://mlsanity.com/paper/2002.12764/) (2020)
- [Unsupervised Learning of Semantic Audio Representations](https://mlsanity.com/paper/1711.02209/) (2017)
- [Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline](https://mlsanity.com/paper/1803.10109/) (2018)
- [Learning Noise-Invariant Representations for Robust Speech Recognition](https://mlsanity.com/paper/1807.06610/) (2018)
- [FEARLESS STEPS Challenge (FS-2): Supervised Learning with Massive Naturalistic Apollo Data](https://mlsanity.com/paper/2008.06764/) (2020)
- ["This is Houston. Say again, please". The Behavox system for the Apollo-11 Fearless Steps Challenge (phase II)](https://mlsanity.com/paper/2008.01504/) (2020)
- [Frustratingly Easy Noise-aware Training of Acoustic Models](https://mlsanity.com/paper/2011.02090/) (2020)
- [UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation](https://mlsanity.com/paper/1610.07651/) (2016)

## Built on by (most cited first, 4 of 4)

- [Content-Context Factorized Representations for Automated Speech Recognition](https://mlsanity.com/paper/2205.09872/) (2022)
- [A Conformer Based Acoustic Model for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2203.00725/) (2022)
- [FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition](https://mlsanity.com/paper/2206.15056/) (2022)
- [MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition](https://mlsanity.com/paper/2310.18450/) (2023)

## Abstract (arXiv)

In this study, we propose to investigate triplet loss for the purpose of an alternative feature representation for ASR. We consider a general non-semantic speech representation, which is trained with a self-supervised criteria based on triplet loss called TRILL, for acoustic modeling to represent the acoustic characteristics of each audio. This strategy is then applied to the CHiME-4 corpus and CRSS-UTDallas Fearless Steps Corpus, with emphasis on the 100-hour challenge corpus which consists of 5 selected NASA Apollo-11 channels. An analysis of the extracted embeddings provides the foundation needed to characterize training utterances into distinct groups based on acoustic distinguishing properties. Moreover, we also demonstrate that triplet-loss based embedding performs better than i-Vector in acoustic modeling, confirming that the triplet loss is more effective than a speaker feature. With additional techniques such as pronunciation and silence probability modeling, plus multi-style training, we achieve a +5.42% and +3.18% relative WER improvement for the development and evaluation sets of the Fearless Steps Corpus. To explore generalization, we further test the same technique on the 1 channel track of CHiME-4 and observe a +11.90% relative WER improvement for real test data.