Data to 14 Oct 2026

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

arXiv 1512.02595 ↗First posted 8 Dec 2015cs.CLcited by 451

Not on the map. Why?

Abstract (arXiv)

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different languages. Key to our approach is our application of HPC techniques, resulting in a 7x speedup over our previous system. Because of this efficiency, experiments that previously took weeks now run in days. This enables us to iterate more quickly to identify superior architectures and algorithms. As a result, in several cases, our system is competitive with the transcription of human workers when benchmarked on standard datasets. Finally, using a technique called Batch Dispatch with GPUs in the data center, we show that our system can be inexpensively deployed in an online setting, delivering low latency when serving users at scale.

Key facts. Cited by 451 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2017: 1; 2018: 1; 2019: 1; 2020: 0; 2021: 141; 2022: 120; 2023: 78; 2024: 41; 2025: 47; 2026: 21.

451 papers.

Sort:

By area:

2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 399
2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
2021Curriculum Learning: A Surveycited by 259
2021Factorized Fourier Neural Operatorscited by 249
2024AnyGPT: Unified Multimodal LLM with Discrete Sequence Modelingcited by 217
2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 197
2022Compute Trends Across Three Eras of Machine Learningcited by 163
2021Unsupervised Speech Recognitioncited by 148
2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 148

38 more

2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
2023End-to-End Speech Recognition: A Surveycited by 129
2023Dataset Distillation: A Comprehensive Reviewcited by 127
2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 125
2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
2021The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usagecited by 101
2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
2022Physics-Informed Machine Learning: A Survey on Problems, Methods and Applicationscited by 92
2023SyncTalk: The Devil is in the Synchronization for Talking Head Synthesiscited by 86
2021Federated Quantum Machine Learningcited by 82
2022AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionscited by 82
2022Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decompositioncited by 81
2023Efficient Emotional Adaptation for Audio-Driven Talking-Head Generationcited by 81
2022DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Renderingcited by 80
2021Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyondcited by 76
2022Robust Self-Supervised Audio-Visual Speech Recognitioncited by 75
2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
2023Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lecturescited by 68
2021Handcrafted Backdoors in Deep Neural Networkscited by 63
2022Toward a realistic model of speech processing in the brain with self-supervised learningcited by 63
2025RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMscited by 61
2022Transferability in Deep Learning: A Surveycited by 57
2023Can Generative Large Language Models Perform ASR Error Correction?cited by 57
2023Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognitioncited by 56
2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
2022GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicalitycited by 52
2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 52
2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 47
2022Towards End-to-end Unsupervised Speech Recognitioncited by 45
2021Consistency Regularization for Adversarial Robustnesscited by 42
2023Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoringcited by 42
2022Lip to Speech Synthesis with Visual Context Attentional GANcited by 41
2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 40
2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
2022Self-supervised models of audio effectively explain human cortical responses to speechcited by 37
2022The Neural Race Reduction: Dynamics of Abstraction in Gated Networkscited by 37

50 most cited of 451 All 451 (JSON)