Conformer

Latest papers

12 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale
Oct 9, 2026Yaroslav Getman, Tamás Grósz, Tommi Lehtonen +1Conformer Speech Processing
Dept. lnformation and Communications Engineering Aalto University Espoo, Finland · Walton Institute, South East Technological University, Ireland Aalto University Espoo, Finland · Finnish National Audiovisual Institute (KAVI) Helsinki, Finland
Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech
Sep 27, 2026Nicola Barbaro, Cristina Gena, Francesco Petriglia +3Conformer Automatic Speech Recognition
University of Turin, Computer Science Department, Via Pessinetto 12, 10149 Turin, Italy · Fondazione Paideia Ente Filantropico, Via Moncalvo 1, 10131 Turin, Italy
Design of the IBM Granite 5.0 TurboCTC ASR Model
Sep 17, 2026Brian Kingsbury, George Saon, Masayuki Suzuki +5Transformer Connectionist Temporal Classification
IBM Research
The Anatomy of an ASR Hallucination
Sep 3, 2026Hamees Sayed, Apoorv Singh, Kumar Aman +1Robust ASR Conformer
Smallest AI · Fast Code AI
EnsembleEGNN: Set-Based Graph Learning for Thermodynamic Ensembles of Cyclic Peptides
Jul 23, 2026Aaron L. Feller, Kris Deibler, Maxim SecorEquivariant GNNs Molecular Property Prediction
Interdisciplinary Life Sciences, University of Texas at Austin, Austin, TX. · Molecular AI, Novo Nordisk, Lexington, MA.
Boltzmann-Expected Molecular Design with Decoupled Annealing Flows
Jul 21, 2026Selma Moqvist, Richard Beckmann, Ross Irwin +2Molecular Optimization Molecular Graph Generation
Department of Computer Science and Engineering Chalmers University of Technology & University of Gothenburg SE-41296 Gothenburg, Sweden · Molecular AI Discovery Sciences, R&D AstraZeneca SE-43183 Mölndal, Sweden
Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization
Jul 11, 2026Shuhai Peng, Jinjiang Liu, Hui Lu +5Target Speaker Extraction Speech Processing
Tsinghua University · The Chinese University of Hong Kong · SenseTime
QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
Jun 17, 2026Shogo Yamauchi, Hideaki Tamori, Makoto Sakai +2Transformer Complex-Valued Neural Networks
The Asahi Shimbun Company, Japan · Tokyo Woman’s Christian University, Japan
End-to-End Intracortical Speech Decoding from Neural Activity
May 23, 2026Owais Mujtaba Khanday, Jose A. Gonzalez-Lopez, Marc Ouellet +2Brain-Computer Interfaces Neural Decoding
1Dpt. of Signal Theory, Telematics and Communications, University of Granada, Spain · 2Brain, Mind, and Behavior Research Center, University of Granada, Spain · 3Grupo CSUR de Epilepsia Refractaria, Hospital Virgen de Las Nieves (Granada), Spain
FlashMol: High-Quality Molecule Generation in as Few as Four Steps
May 7, 2026Xinyuan Wei, Zian Li, Shaoheng Yan +2Diffusion Distillation Few-Step Diffusion Sampling
Institute for Artificial Intelligence, Peking University · Yuanpei College, Peking University · School of Intelligence Science and Technology, Peking University +2
iPhoneme: Brain-to-Text Communication for ALS Using ConformerXL Decoding
Apr 7, 2026Yoonmin Cha, Dawit Chun, Sung ParkConformer Brain-Computer Interfaces
School of Data Science and Artificial Intelligence, Taejae University
CIPHER: Conformer-based Inference of Phonemes from High-density EEG
Mar 22, 2026Varshith MadishettyEEG-to-Text Decoding Conformer

Oct 9, 2026J/K move · Enter open · S save

From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale

Yaroslav Getman, Tamás Grósz, Tommi Lehtonen, Mikko Kurimo

Dept. lnformation and Communications Engineering Aalto University Espoo, Finland · Walton Institute, South East Technological University, Ireland Aalto University Espoo, Finland · Finnish National Audiovisual Institute (KAVI) Helsinki, Finland

Conformer Speech Processing Self-Supervised Speech Representation Learning Transformer Automatic Speech Recognition Low-Resource Speech Recognition

Open paper AskPDF arXiv

Broadcast archives offer scale and diversity for self-supervised learning (SSL) but contain substantial noisy, non-speech, and multilingual content. Prior work typically relies on voice activity detection or language identification (LID) to extract speech, ensuring presence rather than quality. Whether and how to filter unlabeled speech by quality for SSL, particularly from noisy broadcasts, remains underexplored. We present a large-scale Finnish SSL study starting from 2.1M hours of unconstrained broadcast audio. We propose automatic speech recognition (ASR) confidence as a proxy for pretraining data quality and show 3-7% relative WER improvements over LID-based filtering despite a smaller training set. We further address the lack of controlled architectural comparisons in speech SSL by evaluating Transformer, Macaron-Net, Conformer, and E-Branchformer at matched parameter budgets. Our models improve upon prior Finnish SSL baselines, particularly at Base scale and out-of-domain.