# CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition

arXiv: https://arxiv.org/abs/1905.11235 · HTML: https://mlsanity.com/paper/1905.11235/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 30 of 77)

- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [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)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages](https://mlsanity.com/paper/2305.04160/) (2023)
- [FunASR: A Fundamental End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2305.11013/) (2023)
- [An Embarrassingly Simple Approach for LLM with Strong ASR Capacity](https://mlsanity.com/paper/2402.08846/) (2024)
- [Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection](https://mlsanity.com/paper/2201.12806/) (2022)
- [Learning When to Translate for Streaming Speech](https://mlsanity.com/paper/2109.07368/) (2021)
- [A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation](https://mlsanity.com/paper/2110.05249/) (2021)
- [SimulSLT: End-to-End Simultaneous Sign Language Translation](https://mlsanity.com/paper/2112.04228/) (2021)
- [SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2210.08634/) (2022)
- [End-to-End Simultaneous Speech Translation with Differentiable Segmentation](https://mlsanity.com/paper/2305.16093/) (2023)
- [Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks](https://mlsanity.com/paper/2305.03101/) (2023)
- [SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability](https://mlsanity.com/paper/2308.03266/) (2023)
- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [SSR: Alignment-Aware Modality Connector for Speech Language Models](https://mlsanity.com/paper/2410.00168/) (2024)
- [Accelerating Transducers through Adjacent Token Merging](https://mlsanity.com/paper/2306.16009/) (2023)
- [Improving CTC-based speech recognition via knowledge transferring from pre-trained language models](https://mlsanity.com/paper/2203.03582/) (2022)
- [Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation](https://mlsanity.com/paper/2204.09595/) (2022)
- [Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognition](https://mlsanity.com/paper/2103.00422/) (2021)
- [Speech Recognition by Simply Fine-tuning BERT](https://mlsanity.com/paper/2102.00291/) (2021)
- [CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR](https://mlsanity.com/paper/2203.16758/) (2022)
- [Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation](https://mlsanity.com/paper/2301.13003/) (2023)
- [Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Model](https://mlsanity.com/paper/2301.12343/) (2023)
- [BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition](https://mlsanity.com/paper/2310.02629/) (2023)
- [End-to-End Speech-to-Text Translation: A Survey](https://mlsanity.com/paper/2312.01053/) (2023)
- [BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation](https://mlsanity.com/paper/2405.19041/) (2024)
- [On Compressing Sequences for Self-Supervised Speech Models](https://mlsanity.com/paper/2210.07189/) (2022)
- [Mamba for Streaming ASR Combined with Unimodal Aggregation](https://mlsanity.com/paper/2410.00070/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With the joint action of these methods, the CIF-based model shows competitive performance. Notably, it achieves a word error rate (WER) of 2.86% on the test-clean of Librispeech and creates new state-of-the-art result on Mandarin telephone ASR benchmark.