Data to 7 Oct 2026

Listen, Attend and Spell

arXiv 1508.01211 ↗First posted 5 Aug 2015cs.CL cs.LG cs.NEcited by 542

Not on the map. Why?

Abstract (arXiv)

We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent network encoder that accepts filter bank spectra as inputs. The speller is an attention-based recurrent network decoder that emits characters as outputs. The network produces character sequences without making any independence assumptions between the characters. This is the key improvement of LAS over previous end-to-end CTC models. On a subset of the Google voice search task, LAS achieves a word error rate (WER) of 14.1% without a dictionary or a language model, and 10.3% with language model rescoring over the top 32 beams. By comparison, the state-of-the-art CLDNN-HMM model achieves a WER of 8.0%.

Key facts. Cited by 542 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 144; 2022: 128; 2023: 120; 2024: 68; 2025: 48; 2026: 33.

542 papers.

Sort:

By area:

2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
2023Google USM: Scaling Automatic Speech Recognition Beyond 100 Languagescited by 228
2021WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognitioncited by 189
2021A Survey on Neural Speech Synthesiscited by 182
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
2023Neural Architecture Search: Insights from 1000 Paperscited by 136
2023End-to-End Speech Recognition: A Surveycited by 127
2022Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)cited by 115
2022Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidationcited by 113
2026Qwen3-ASR Technical Reportcited by 105

38 more

2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
2023FunASR: A Fundamental End-to-End Speech Recognition Toolkitcited by 92
2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 90
2023Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labellingcited by 87
2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 86
2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 76
2021A Practical Survey on Faster and Lighter Transformerscited by 73
2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
2021Annealing Knowledge Distillationcited by 61
2021Sub-word Level Lip Reading With Visual Attentioncited by 60
2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
2021BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?cited by 56
2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
2023Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognitioncited by 56
2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
2021LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speechcited by 46
2022WeNet 2.0: More Productive End-to-End Speech Recognition Toolkitcited by 46
2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
2021With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognitioncited by 41
2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
2021Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASRcited by 40
2022Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selectioncited by 39
2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
2021Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognitioncited by 37
2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 37
2022Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Datasetcited by 36
2023AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translationcited by 35
2024LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASRcited by 35
2021SynthASR: Unlocking Synthetic Data for Speech Recognitioncited by 34
2022RescoreBERT: Discriminative Speech Recognition Rescoring with BERTcited by 34
2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
2022Attention as a Guide for Simultaneous Speech Translationcited by 32
2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
2021Factorized Neural Transducer for Efficient Language Model Adaptationcited by 31
2023MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognitioncited by 31

50 most cited of 542 All 542 (JSON)