Data to 7 Oct 2026

Cold Fusion: Training Seq2Seq Models Together with Language Models

arXiv 1708.06426 ↗First posted 21 Aug 2017cs.CLcited by 87

Not on the map. Why?

Abstract (arXiv)

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by leveraging unlabeled data, often in the form of a language model. In this work, we present the Cold Fusion method, which leverages a pre-trained language model during training, and show its effectiveness on the speech recognition task. We show that Seq2Seq models with Cold Fusion are able to better utilize language information enjoying i) faster convergence and better generalization, and ii) almost complete transfer to a new domain while using less than 10% of the labeled training data.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 21; 2023: 20; 2024: 6; 2025: 8; 2026: 7.

87 papers.

Sort:

2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
2023End-to-End Speech Recognition: A Surveycited by 127
2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
2023Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognitioncited by 48
2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
2021Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERTcited by 31
2022Visualize Before You Write: Imagination-Guided Open-Ended Text Generationcited by 30
2021Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Modelscited by 25
2021Injecting Text in Self-Supervised Speech Pretrainingcited by 24

38 more

2023An Overview on Language Models: Recent Developments and Outlookcited by 22
2024It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognitioncited by 22
2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
2024Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Searchcited by 19
2021Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognitioncited by 17
2021Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognitioncited by 17
2021Transformer Language Models with LSTM-based Cross-utterance Information Representationcited by 15
2021Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Modelcited by 14
2023Large-scale Language Model Rescoring on Long-form Datacited by 14
2023CopyNE: Better Contextual ASR by Copying Named Entitiescited by 13
2023Multi-stage Large Language Model Correction for Speech Recognitioncited by 13
2021Adapting Long Context NLM for ASR Rescoring in Conversational Agentscited by 12
2022Improving Rare Word Recognition with LM-aware MWER Trainingcited by 12
2022BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Modelcited by 11
2023Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillationcited by 11
2021Lookup-Table Recurrent Language Models for Long Tail Speech Recognitioncited by 9
2022Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASRcited by 9
2024Contextualized Automatic Speech Recognition with Dynamic Vocabularycited by 8
2021Language model fusion for streaming end to end speech recognitioncited by 7
2021Prose2Poem: The Blessing of Transformers in Translating Prose to Persian Poetrycited by 7
2025Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuningcited by 7
2021Code Generation from Natural Language with Less Prior and More Monolingual Datacited by 6
2021Multimodal Conditionality for Natural Language Generationcited by 6
2022Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Modelcited by 6
2022Neural-FST Class Language Model for End-to-End Speech Recognitioncited by 6
2022Reducing language context confusion for end-to-end code-switching automatic speech recognitioncited by 6
2022Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translationcited by 6
2023Acoustic Model Fusion for End-to-end Speech Recognitioncited by 6
2021On-Device Personalization of Automatic Speech Recognition Models for Disordered Speechcited by 5
2022Adaptive Discounting of Implicit Language Models in RNN-Transducerscited by 5
2022Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognitioncited by 5
2022Relaxed Attention for Transformer Modelscited by 5
2022Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognitioncited by 5
2023Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimationcited by 5
2023Text-only Domain Adaptation using Unified Speech-Text Representation in Transducercited by 5
2024Revisiting ASR Error Correction with Specialized Modelscited by 5
2025Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognitioncited by 5
2021Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognitioncited by 4

50 most cited of 87 All 87 (JSON)