Data to 7 Oct 2026

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

arXiv 1905.11235 ↗First posted 27 May 2019cs.CL cs.LG cs.NEcited by 76

Not on the map. Why?

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.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 21; 2024: 17; 2025: 12; 2026: 4.

76 papers.

Sort:

By area:

2024MM-LLMs: Recent Advances in MultiModal Large Language Modelscited by 277
2022Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognitioncited by 139
2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
2023End-to-End Speech Recognition: A Surveycited by 127
2023X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languagescited by 127
2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
2021Learning When to Translate for Streaming Speechcited by 30
2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
2021SimulSLT: End-to-End Simultaneous Sign Language Translationcited by 26
2022SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learningcited by 26

38 more

2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
2023Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Taskscited by 20
2021Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognitioncited by 17
2023SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Abilitycited by 16
2024SSR: Alignment-Aware Modality Connector for Speech Language Modelscited by 16
2022Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelscited by 14
2022Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translationcited by 14
2023Accelerating Transducers through Adjacent Token Mergingcited by 14
2021Speech Recognition by Simply Fine-tuning BERTcited by 11
2021Alignment Knowledge Distillation for Online Streaming Attention-based Speech Recognitioncited by 11
2022CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASRcited by 11
2023Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillationcited by 11
2023Achieving Timestamp Prediction While Recognizing with Non-Autoregressive End-to-End ASR Modelcited by 9
2023End-to-End Speech-to-Text Translation: A Surveycited by 9
2023BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognitioncited by 8
2024BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillationcited by 8
2022On Compressing Sequences for Self-Supervised Speech Modelscited by 7
2024Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detectioncited by 7
2024Mamba for Streaming ASR Combined with Unimodal Aggregationcited by 7
2023Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inferencecited by 6
2023CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognitioncited by 6
2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
2024Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translationcited by 5
2022Speech-text based multi-modal training with bidirectional attention for improved speech recognitioncited by 4
2024How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Notcited by 4
2022AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translationcited by 3
2023CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Trainingcited by 3
2024Large Generative Model-assisted Talking-face Semantic Communication Systemcited by 3
2025SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniorscited by 3
2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translationcited by 3
2021Towards efficient end-to-end speech recognition with biologically-inspired neural networkscited by 2
2022Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRcited by 2
2022Once-for-All Sequence Compression for Self-Supervised Speech Modelscited by 2
2023LiteG2P: A fast, light and high accuracy model for grapheme-to-phoneme conversioncited by 2
2023Language-Universal Adapter Learning with Knowledge Distillation for End-to-End Multilingual Speech Recognitioncited by 2
2023Unimodal Aggregation for CTC-based Speech Recognitioncited by 2
2024Streaming Sequence Transduction through Dynamic Compressioncited by 2
2024SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image datacited by 2

50 most cited of 76 All 76 (JSON)