# 4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders

arXiv: https://arxiv.org/abs/2212.10818 · HTML: https://mlsanity.com/paper/2212.10818/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [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)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context](https://mlsanity.com/paper/2005.03191/) (2020)
- [Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer](https://mlsanity.com/paper/1801.00841/) (2018)
- [Intermediate Loss Regularization for CTC-based Speech Recognition](https://mlsanity.com/paper/2102.03216/) (2021)
- [QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions](https://mlsanity.com/paper/1910.10261/) (2019)
- [Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict](https://mlsanity.com/paper/2005.08700/) (2020)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [Two-Pass End-to-End Speech Recognition](https://mlsanity.com/paper/1908.10992/) (2019)
- [Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation](https://mlsanity.com/paper/1904.07209/) (2019)
- [Transformer Based Deliberation for Two-Pass Speech Recognition](https://mlsanity.com/paper/2101.11577/) (2021)
- [First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs](https://mlsanity.com/paper/1408.2873/) (2014)
- [CTC Alignments Improve Autoregressive Translation](https://mlsanity.com/paper/2210.05200/) (2022)
- [Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input](https://mlsanity.com/paper/2010.15025/) (2020)
- [Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding](https://mlsanity.com/paper/2112.11442/) (2021)
- [TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition](https://mlsanity.com/paper/2104.01522/) (2021)
- [Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LM](https://mlsanity.com/paper/2209.04062/) (2022)

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

- [Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search](https://mlsanity.com/paper/2401.10449/) (2024)
- [Contextualized End-to-end Automatic Speech Recognition with Intermediate Biasing Loss](https://mlsanity.com/paper/2406.16120/) (2024)
- [Contextualized Automatic Speech Recognition with Dynamic Vocabulary](https://mlsanity.com/paper/2405.13344/) (2024)
- [Joint Beam Search Integrating CTC, Attention, and Transducer Decoders](https://mlsanity.com/paper/2406.02950/) (2024)
- [Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask](https://mlsanity.com/paper/2406.10034/) (2024)
- [Enhanced Hybrid Transducer and Attention Encoder Decoder with Text Data](https://mlsanity.com/paper/2506.19159/) (2025)
- [Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation](https://mlsanity.com/paper/2405.13514/) (2024)

## Abstract (arXiv)

The network architecture of end-to-end (E2E) automatic speech recognition (ASR) can be classified into several models, including connectionist temporal classification (CTC), recurrent neural network transducer (RNN-T), attention mechanism, and non-autoregressive mask-predict models. Since each of these network architectures has pros and cons, a typical use case is to switch these separate models depending on the application requirement, resulting in the increased overhead of maintaining all models. Several methods for integrating two of these complementary models to mitigate the overhead issue have been proposed; however, if we integrate more models, we will further benefit from these complementary models and realize broader applications with a single system. This paper proposes four-decoder joint modeling (4D) of CTC, attention, RNN-T, and mask-predict, which has the following three advantages: 1) The four decoders are jointly trained so that they can be easily switched depending on the application scenarios. 2) Joint training may bring model regularization and improve the model robustness thanks to their complementary properties. 3) Novel one-pass joint decoding methods using CTC, attention, and RNN-T further improves the performance. The experimental results showed that the proposed model consistently reduced the WER.