# A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition

arXiv: https://arxiv.org/abs/2005.10113 · HTML: https://mlsanity.com/paper/2005.10113/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2020.

## Built on by (most cited first, 8 of 8)

- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation](https://mlsanity.com/paper/2204.09595/) (2022)
- [Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff](https://mlsanity.com/paper/2309.11379/) (2023)
- [CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition](https://mlsanity.com/paper/2307.14132/) (2023)
- [Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization](https://mlsanity.com/paper/2509.15579/) (2025)
- [VAD-free Streaming Hybrid CTC/Attention ASR for Unsegmented Recording](https://mlsanity.com/paper/2107.07509/) (2021)
- [Lightweight Transducer Based on Frame-Level Criterion](https://mlsanity.com/paper/2409.13698/) (2024)
- [Transducer Consistency Regularization for Speech to Text Applications](https://mlsanity.com/paper/2410.07491/) (2024)

## Abstract (arXiv)

End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text label sequence by neural networks. According to the driving end in the recognition process, end-to-end ASR models could be categorized into two types: label-synchronous and frame-synchronous, each of which has unique model behaviour and characteristic. In this work, we make a detailed comparison on a representative label-synchronous model (transformer) and a soft frame-synchronous model (continuous integrate-and-fire (CIF) based model). The results on three public dataset and a large-scale dataset with 12000 hours of training data show that the two types of models have respective advantages that are consistent with their synchronous mode.