Data to 14 Oct 2026

Deep Speech: Scaling up end-to-end speech recognition

arXiv 1412.5567 ↗First posted 17 Dec 2014cs.CL cs.LG cs.NEcited by 354

Not on the map. Why?

Abstract (arXiv)

We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.

Key facts. Cited by 354 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 112; 2022: 80; 2023: 69; 2024: 39; 2025: 36; 2026: 18.

354 papers.

Sort:

By area:

2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
2021MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglementcited by 190
2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 154
2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
2023Neural Architecture Search: Insights from 1000 Paperscited by 139
2023DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animationcited by 136
2023GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesiscited by 131
2023End-to-End Speech Recognition: A Surveycited by 129
2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 115
2021A Survey on Data Augmentation for Text Classificationcited by 111
2021Learning Speech-driven 3D Conversational Gestures from Videocited by 98

38 more

2022Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesiscited by 97
2021Trustworthy AI: A Computational Perspectivecited by 93
2022E-Branchformer: Branchformer with Enhanced merging for speech recognitioncited by 92
2021FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learningcited by 90
2022ZeroEGGS: Zero-shot Example-based Gesture Generation from Speechcited by 84
2021Federated Quantum Machine Learningcited by 82
2023DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Modelscited by 81
2021Visual Alignment Constraint for Continuous Sign Language Recognitioncited by 80
2022Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Trainingcited by 79
2023FaceDiffuser: Speech-Driven 3D Facial Animation Synthesis Using Diffusioncited by 78
2022Imitator: Personalized Speech-driven 3D Facial Animationcited by 74
2023DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Videocited by 74
2023Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesiscited by 72
2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
2021LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalizationcited by 67
2021Handcrafted Backdoors in Deep Neural Networkscited by 63
2024TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splattingcited by 60
2022VeLO: Training Versatile Learned Optimizers by Scaling Upcited by 57
2021Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesiscited by 56
2023Relational Deep Learning: Graph Representation Learning on Relational Databasescited by 56
2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
2021A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimizationcited by 46
2022Emotion-Controllable Generalized Talking Face Generationcited by 43
2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
2023Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoringcited by 42
2023GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generationcited by 42
2021With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognitioncited by 41
2022Lip to Speech Synthesis with Visual Context Attentional GANcited by 41
2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 40
2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 38
2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
2021Live Speech Portraits: Real-Time Photorealistic Talking-Head Animationcited by 36
2021An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systemscited by 32
2024Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysiscited by 31
2021End-to-End Speech Recognition from Federated Acoustic Modelscited by 30
2021On the limit of English conversational speech recognitioncited by 30
2022Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Datacited by 30
2022iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detectioncited by 27

50 most cited of 354 All 354 (JSON)