# Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2104.01721 · HTML: https://mlsanity.com/paper/2104.01721/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2021.

## Built on by (most cited first, 30 of 34)

- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Squeezeformer: An Efficient Transformer for Automatic Speech Recognition](https://mlsanity.com/paper/2206.00888/) (2022)
- [Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition](https://mlsanity.com/paper/2109.01163/) (2021)
- [A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation](https://mlsanity.com/paper/2110.05249/) (2021)
- [Audio-Visual Efficient Conformer for Robust Speech Recognition](https://mlsanity.com/paper/2301.01456/) (2023)
- [CTC Variations Through New WFST Topologies](https://mlsanity.com/paper/2110.03098/) (2021)
- [Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units](https://mlsanity.com/paper/2110.04109/) (2021)
- [SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition](https://mlsanity.com/paper/2212.01039/) (2022)
- [VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing](https://mlsanity.com/paper/2404.06674/) (2024)
- [Decoupling recognition and transcription in Mandarin ASR](https://mlsanity.com/paper/2108.01129/) (2021)
- [A Toolbox for Construction and Analysis of Speech Datasets](https://mlsanity.com/paper/2104.04896/) (2021)
- [A Compact End-to-End Model with Local and Global Context for Spoken Language Identification](https://mlsanity.com/paper/2210.15781/) (2022)
- [Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition](https://mlsanity.com/paper/2211.15075/) (2022)
- [Improving CTC-based ASR Models with Gated Interlayer Collaboration](https://mlsanity.com/paper/2205.12462/) (2022)
- [Are E2E ASR models ready for an industrial usage?](https://mlsanity.com/paper/2112.12572/) (2021)
- [Seq-2-Seq based Refinement of ASR Output for Spoken Name Capture](https://mlsanity.com/paper/2203.15833/) (2022)
- [Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy](https://mlsanity.com/paper/2303.07687/) (2023)
- [Trustera: A Live Conversation Redaction System](https://mlsanity.com/paper/2303.09438/) (2023)
- [Enhancing Unsupervised Speech Recognition with Diffusion GANs](https://mlsanity.com/paper/2303.13559/) (2023)
- [Non-autoregressive real-time Accent Conversion model with voice cloning](https://mlsanity.com/paper/2405.13162/) (2024)
- [A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition](https://mlsanity.com/paper/2606.19747/) (2026)
- [ASR in German: A Detailed Error Analysis](https://mlsanity.com/paper/2204.05617/) (2022)
- [InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition](https://mlsanity.com/paper/2305.16342/) (2023)
- [Weak Alignment Supervision from Hybrid Model Improves End-to-end ASR](https://mlsanity.com/paper/2311.14835/) (2023)
- [Visual-Aware Speech Recognition for Noisy Scenarios](https://mlsanity.com/paper/2504.07229/) (2025)
- [Improving Self-Supervised Learning-based MOS Prediction Networks](https://mlsanity.com/paper/2204.11030/) (2022)
- [Deep Sparse Conformer for Speech Recognition](https://mlsanity.com/paper/2209.00260/) (2022)
- [Attention Enhanced Citrinet for Speech Recognition](https://mlsanity.com/paper/2209.00261/) (2022)
- [E2E Spoken Entity Extraction for Virtual Agents](https://mlsanity.com/paper/2302.10186/) (2023)
- [Alternating Weak Triphone/BPE Alignment Supervision from Hybrid Model Improves End-to-End ASR](https://mlsanity.com/paper/2402.15594/) (2024)

## Abstract (arXiv)

We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best autoregressive Transducer models.