No article text was recorded for this version.
shallow fusion
Version 2 of 2139 papers176 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Early Stage LM Integration Using Local and Global Log-Linear Combination
- Blog: Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling
- Blog: A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition
- Blog: Espresso: A Fast End-to-end Neural Speech Recognition Toolkit
- Blog: Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition
- Blog: Improving the Performance of Online Neural Transducer Models
- Blog: Language model fusion for streaming end to end speech recognition
- Blog: Attention-Based End-to-End Speech Recognition in Mandarin
- Blog: Improved training of end-to-end attention models for speech recognition
- Blog: Golos: Russian Dataset for Speech Research
- Blog: Librispeech Transducer Model with Internal Language Model Prior Correction
- Blog: Integrating Language Models into Direct Speech Translation: An Inference-Time Solution to Control Gender Inflection
- Blog: SLUE: New Benchmark Tasks For Spoken Language Understanding Evaluation on Natural Speech
- Blog: Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource setting
- Blog: Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
- Blog: Massive End-to-end Models for Short Search Queries
- Blog: Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model
- Blog: Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
- Blog: Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching
- Blog: An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model
- Blog: Conversational Speech Recognition Needs Data? Experiments with Austrian German
- Blog: Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
- Blog: WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
- Blog: Leveraging State-of-the-art ASR Techniques to Audio Captioning
- Blog: Massively Multilingual Shallow Fusion with Large Language Models
- Blog: Cross-Modal Transformer-Based Neural Correction Models for Automatic Speech Recognition
- Blog: A comparable study of modeling units for end-to-end Mandarin speech recognition
- Blog: Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text
- Blog: RWTH ASR Systems for LibriSpeech: Hybrid vs Attention - w/o Data Augmentation
- Blog: ÌròyìnSpeech: A Multi-purpose Yorùbá Speech Corpus
- Blog: Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages
- Blog: On the Interpretability of Deep Learning Models for Collaborative Argumentation Analysis in Classrooms
- Blog: Single Headed Attention Based Sequence-to-Sequence Model for State-of-the-Art Results on Switchboard
- Blog: Listen, Attend, Spell and Adapt: Speaker Adapted Sequence-to-Sequence ASR
- Blog: UserLibri: A Dataset for ASR Personalization Using Only Text
- Blog: Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks
- Blog: BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
- Blog: Retrieval Augmented End-to-End Spoken Dialog Models
- Blog: Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
- Blog: Integration of language identification into a recognition system for spoken conversations containing code-Switches
- Blog: Deep Audio-Visual Speech Recognition
- Blog: Language Model Applications to Spelling with Brain-Computer Interfaces
- Blog: An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition
- Blog: OkwuGbé: End-to-End Speech Recognition for Fon and Igbo
- Blog: A review of on-device fully neural end-to-end automatic speech recognition algorithms
- Blog: Training a Speech-to-Text Model for Dutch on the Corpus Gesproken Nederlands
- Blog: Low-resource speech recognition and dialect identification of Irish in a multi-task framework
- Blog: Maximum a posteriori Based Decoding for CTC Acoustic Models
- Blog: Combining multiple-sized sub-word units in a speech recognition system using baseform selection
- Blog: Transsion TSUP's speech recognition system for ASRU 2023 MADASR Challenge
- Blog: An Automatic Speech Recognition System for the Italian Language
- Blog: Improving Transformer-Based End-to-End Speech Recognition with Connectionist Temporal Classification and Language Model Integration
- Blog: Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding
- Blog: CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR
- Blog: Improved Training of End-to-end Attention Models for Speech Recognition
- Blog: Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
- Blog: Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR
- Blog: Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
- Blog: Towards Inclusive and Fair ASR: Insights from the SAPC Challenge for Optimizing Disordered Speech Recognition
- Blog: A Likelihood Ratio based Domain Adaptation Method for E2E Models
Showing 60 of 139 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_shallow_fusion_66617f0a,
title = {shallow fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shallow-fusion/rdr_66617f0a89bf4d4c80293ea5dbeaa90e},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_shallow_fusion_66617f0a_v2,
title = {shallow fusion},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shallow-fusion/rdr_66617f0a89bf4d4c80293ea5dbeaa90e/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}