# CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition

arXiv: https://arxiv.org/abs/2010.14725 · HTML: https://mlsanity.com/paper/2010.14725/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond](https://mlsanity.com/paper/2204.09269/) (2022)
- [Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions](https://mlsanity.com/paper/2104.02724/) (2021)
- [Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey](https://mlsanity.com/paper/2403.01255/) (2024)
- [Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models](https://mlsanity.com/paper/2107.09428/) (2021)
- [Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates](https://mlsanity.com/paper/2109.12804/) (2021)
- [An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition](https://mlsanity.com/paper/2106.09885/) (2021)
- [TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition](https://mlsanity.com/paper/2104.01522/) (2021)
- [Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition](https://mlsanity.com/paper/2109.06684/) (2021)
- [A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognition](https://mlsanity.com/paper/2304.07611/) (2023)
- [Improving CTC-based ASR Models with Gated Interlayer Collaboration](https://mlsanity.com/paper/2205.12462/) (2022)
- [Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition](https://mlsanity.com/paper/2209.15176/) (2022)
- [Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy](https://mlsanity.com/paper/2303.07687/) (2023)
- [Sim-T: Simplify the Transformer Network by Multiplexing Technique for Speech Recognition](https://mlsanity.com/paper/2304.04991/) (2023)
- [Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal Language Model Estimation](https://mlsanity.com/paper/2305.03837/) (2023)
- [UniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models](https://mlsanity.com/paper/2402.08898/) (2024)
- [Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing](https://mlsanity.com/paper/2509.16622/) (2025)
- [Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition](https://mlsanity.com/paper/2210.14725/) (2022)
- [A Lexical-aware Non-autoregressive Transformer-based ASR Model](https://mlsanity.com/paper/2305.10839/) (2023)
- [GNCformer Enhanced Self-attention for Automatic Speech Recognition](https://mlsanity.com/paper/2305.12755/) (2023)
- [DESign: Dynamic Context-Aware Convolution and Efficient Subnet Regularization for Continuous Sign Language Recognition](https://mlsanity.com/paper/2507.03339/) (2025)
- [H-PRM: A Pluggable Hotword Pre-Retrieval Module for Various Speech Recognition Systems](https://mlsanity.com/paper/2508.18295/) (2025)
- [M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR](https://mlsanity.com/paper/2510.22172/) (2025)

## Abstract (arXiv)

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of acoustics for each token. The information are used to extract acoustic representation for each token in parallel, referred to as token-level acoustic embedding which substitutes the word embedding in autoregressive transformer (AT) to achieve parallel generation in decoder. During inference, an error-based alignment sampling method is proposed to be applied to the CTC output space, reducing the WER and retaining the parallelism as well. Experimental results show that the proposed method achieves WERs of 3.8%/9.1% on Librispeech test clean/other dataset without an external LM, and a CER of 5.8% on Aishell1 Mandarin corpus, respectively1. Compared to the AT baseline, the CASS-NAT has a performance reduction on WER, but is 51.2x faster in terms of RTF. When decoding with an oracle CTC alignment, the lower bound of WER without LM reaches 2.3% on the test-clean set, indicating the potential of the proposed method.