# Deep CLAS: Deep Contextual Listen, Attend and Spell

arXiv: https://arxiv.org/abs/2409.17603 · HTML: https://mlsanity.com/paper/2409.17603/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 26 Sep 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context](https://mlsanity.com/paper/2005.03191/) (2020)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [Deep Shallow Fusion for RNN-T Personalization](https://mlsanity.com/paper/2011.07754/) (2020)
- [Achieving Human Parity in Conversational Speech Recognition](https://mlsanity.com/paper/1610.05256/) (2016)
- [Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition](https://mlsanity.com/paper/2109.00627/) (2021)
- [Simple Fusion: Return of the Language Model](https://mlsanity.com/paper/1809.00125/) (2018)
- [Contextual Speech Recognition with Difficult Negative Training Examples](https://mlsanity.com/paper/1810.12170/) (2018)
- [Personalized Speech recognition on mobile devices](https://mlsanity.com/paper/1603.03185/) (2016)
- [Spell my name: keyword boosted speech recognition](https://mlsanity.com/paper/2110.02791/) (2021)
- [End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system](https://mlsanity.com/paper/2202.09003/) (2022)
- [Are E2E ASR models ready for an industrial usage?](https://mlsanity.com/paper/2112.12572/) (2021)

## Built on by (most cited first, 2 of 2)

- [PROFASR-BENCH: A Benchmark for Context-Conditioned ASR in High-Stakes Professional Speech](https://mlsanity.com/paper/2512.23686/) (2025)
- [From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs](https://mlsanity.com/paper/2603.24034/) (2026)

## Abstract (arXiv)

Contextual-LAS (CLAS) has been shown effective in improving Automatic Speech Recognition (ASR) of rare words. It relies on phrase-level contextual modeling and attention-based relevance scoring without explicit contextual constraint which lead to insufficient use of contextual information. In this work, we propose deep CLAS to use contextual information better. We introduce bias loss forcing model to focus on contextual information. The query of bias attention is also enriched to improve the accuracy of the bias attention score. To get fine-grained contextual information, we replace phrase-level encoding with character-level encoding and encode contextual information with conformer rather than LSTM. Moreover, we directly use the bias attention score to correct the output probability distribution of the model. Experiments using the public AISHELL-1 and AISHELL-NER. On AISHELL-1, compared to CLAS baselines, deep CLAS obtains a 65.78% relative recall and a 53.49% relative F1-score increase in the named entity recognition scene.