mlsanityData to 7 Oct 2026

Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition

arXiv 2305.05084 ↗First posted 8 May 2023eess.AS cs.SDcited by 120

Not on the map. Why?

Abstract (arXiv)

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigned Conformer with a novel downsampling schema. The proposed model, named Fast Conformer(FC), is 2.8x faster than the original Conformer, supports scaling to Billion parameters without any changes to the core architecture and also achieves state-of-the-art accuracy on Automatic Speech Recognition benchmarks. To enable transcription of long-form speech up to 11 hours, we replaced global attention with limited context attention post-training, while also improving accuracy through fine-tuning with the addition of a global token. Fast Conformer, when combined with a Transformer decoder also outperforms the original Conformer in accuracy and in speed for Speech Translation and Spoken Language Understanding.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 26; 2025: 40; 2026: 47.

120 papers.

Sort:

By area:

  1. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  2. 2025Canary-1B-v2 & Parakeet-TDT-0.6B-v3: Efficient and High-Performance Models for Multilingual ASR and ASTcited by 51
  3. 2024OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identificationcited by 34
  4. 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Modelscited by 29
  5. 2025OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaningcited by 27
  6. 2026Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligencecited by 25
  7. 2024Benchmarking Large Multimodal Models against Common Corruptionscited by 22
  8. 2025Granary: Speech Recognition and Translation Dataset in 25 European Languagescited by 21
  9. 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluationcited by 21
  10. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  11. 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
  12. 2025Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Modelscited by 17
38 more
  1. 2024Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPUcited by 12
  2. 2024Label-Looping: Highly Efficient Decoding for Transducerscited by 9
  3. 2024Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representationscited by 8
  4. 2025Training and Inference Efficiency of Encoder-Decoder Speech Modelscited by 8
  5. 2025Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Playcited by 8
  6. 2024Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformercited by 7
  7. 2024Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spottercited by 7
  8. 2025LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximationcited by 7
  9. 2025NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decodingcited by 7
  10. 2025Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokenscited by 7
  11. 2025Hallucination Benchmark for Speech Foundation Modelscited by 7
  12. 2025Towards Resource-Efficient Compound AI Systemscited by 6
  13. 2025Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMscited by 6
  14. 2025BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognitioncited by 5
  15. 2025SPGISpeech 2.0: Transcribed multi-speaker financial audio for speaker-tagged transcriptioncited by 5
  16. 2026The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoningcited by 5
  17. 2023Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognitioncited by 4
  18. 2024To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillationcited by 4
  19. 2024Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translationcited by 4
  20. 2024Open Universal Arabic ASR Leaderboardcited by 4
  21. 2025ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesiscited by 4
  22. 2025TurboBias: Universal ASR Context-Biasing powered by GPU-accelerated Phrase-Boosting Treecited by 4
  23. 2025MEGConformer: Conformer-Based MEG Decoder for Robust Speech and Phoneme Classificationcited by 4
  24. 2023Long-form Simultaneous Speech Translation: Thesis Proposalcited by 3
  25. 2023How Much Context Does My Attention-Based ASR System Need?cited by 3
  26. 2024AG-LSEC: Audio Grounded Lexical Speaker Error Correctioncited by 3
  27. 2025Unveiling the Best Practices for Applying Speech Foundation Models to Speech Intelligibility Prediction for Hearing-Impaired Peoplecited by 3
  28. 2026Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognitioncited by 3
  29. 2023Big model only for hard audios: Sample dependent Whisper model selection for efficient inferencescited by 2
  30. 2024Linear-Complexity Self-Supervised Learning for Speech Processingcited by 2
  31. 2024ASR Benchmarking: Need for a More Representative Conversational Datasetcited by 2
  32. 2024HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASRcited by 2
  33. 2024High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASRcited by 2
  34. 2025On the Robust Approximation of ASR Metricscited by 2
  35. 2025Large Language Models based ASR Error Correction for Child Conversationscited by 2
  36. 2025PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systemscited by 2
  37. 2025Early Attentive Sparsification Accelerates Neural Speech Transcriptioncited by 2
  38. 2025CAM~OES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguesecited by 2

50 most cited of 120 All 120 (JSON)