mlsanityData to 7 Oct 2026

Streaming End-to-end Speech Recognition For Mobile Devices

arXiv 1811.06621 ↗First posted 15 Nov 2018cs.CLcited by 230

Not on the map. Why?

Abstract (arXiv)

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer. In experimental evaluations, we find that the proposed approach can outperform a conventional CTC-based model in terms of both latency and accuracy in a number of evaluation categories.

Key facts. Cited by 230 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 87; 2022: 65; 2023: 39; 2024: 20; 2025: 11; 2026: 8.

230 papers.

Sort:

By area:

  1. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
  2. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
  3. 2023End-to-End Speech Recognition: A Surveycited by 127
  4. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  5. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  6. 2023Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labellingcited by 87
  7. 2021Top-KAST: Top-K Always Sparse Trainingcited by 79
  8. 2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 76
  9. 2021Annealing Knowledge Distillationcited by 61
  10. 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
  11. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  12. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
38 more
  1. 2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 46
  2. 2022Pruned RNN-T for fast, memory-efficient ASR trainingcited by 46
  3. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  4. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  5. 2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
  6. 2021Tied & Reduced RNN-T Decodercited by 35
  7. 2021SynthASR: Unlocking Synthetic Data for Speech Recognitioncited by 34
  8. 2022RescoreBERT: Discriminative Speech Recognition Rescoring with BERTcited by 34
  9. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  10. 2021Universal Paralinguistic Speech Representations Using Self-Supervised Conformerscited by 32
  11. 2021Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detectioncited by 31
  12. 2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 31
  13. 2023Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Networkcited by 31
  14. 2021Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speechcited by 30
  15. 2021Transformer Based Deliberation for Two-Pass Speech Recognitioncited by 29
  16. 2021Data-Driven Offline Optimization For Architecting Hardware Acceleratorscited by 29
  17. 2021Personalization Strategies for End-to-End Speech Recognition Systemscited by 26
  18. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  19. 2022Streaming End-to-End Multilingual Speech Recognition with Joint Language Identificationcited by 24
  20. 2022JOIST: A Joint Speech and Text Streaming Model For ASRcited by 24
  21. 2021Pseudo-Labeling for Massively Multilingual Speech Recognitioncited by 23
  22. 2023From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognitioncited by 23
  23. 2021Learning Word-Level Confidence For Subword End-to-End ASRcited by 22
  24. 2021Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottleneckscited by 22
  25. 20224-bit Conformer with Native Quantization Aware Training for Speech Recognitioncited by 22
  26. 2022Integrating Text Inputs For Training and Adapting RNN Transducer ASR Modelscited by 20
  27. 2022Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systemscited by 20
  28. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  29. 2021Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Networkcited by 19
  30. 2021On Addressing Practical Challenges for RNN-Transducercited by 19
  31. 2021Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognitioncited by 19
  32. 2022Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizerscited by 19
  33. 2021Dissecting User-Perceived Latency of On-Device E2E Speech Recognitioncited by 18
  34. 2023Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognitioncited by 18
  35. 2022Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systemscited by 17
  36. 2022Accelerating RNN-T Training and Inference Using CTC guidancecited by 17
  37. 2022Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilitiescited by 16
  38. 2022Turn-Taking Prediction for Natural Conversational Speechcited by 15

50 most cited of 230 All 230 (JSON)