Conformer

Latest papers

16 papers4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

NAVE: A Normalized, Adaptive Conformer for Antarctic Whale Vocalization Detection
Nov 6, 2026Matthias Nagl, Paul Primus, Gerhard WidmerSound Event Detection Bioacoustics
Institute of Computational Perception, Johannes Kepler University Linz, Austria · LIT Artificial Intelligence Lab, Linz, Austria
AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models
Oct 28, 2026Pengfei Cai, Katharina S. C. Jäger, Utkarsh Utkarsh +4Constrained Generative Modeling Crystal Structure Generation
Massachusetts Institute of Technology
EVA-Flow: Learning Shared Chemistry for Unified Environment-Aware Molecular Conformation Generation
Oct 26, 2026Bing Yan, Anuroop Sriram, Zachary Ward Ulissi +33D Molecular Generation Molecular Generation
FAIR at Meta · New York University
Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or Hybrid
Oct 26, 2026Tamas Kovacs, Daniel LugerHistorical Document Processing Conformer
University of Graz Department of Digital Humanities · Institut für Österreichische Geschichtsforschung University of Vienna
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

Nov 6, 2026J/K move · Enter open · S save

NAVE: A Normalized, Adaptive Conformer for Antarctic Whale Vocalization Detection

Matthias Nagl, Paul Primus, Gerhard Widmer

Institute of Computational Perception, Johannes Kepler University Linz, Austria · LIT Artificial Intelligence Lab, Linz, Austria

Sound Event Detection Bioacoustics Passive Acoustic Monitoring Conformer

Open paper AskPDF arXiv

Antarctic whale vocalization detection requires temporally localizing call boundaries in long underwater recordings and classifying them into predefined call types. Training reliable machine learning models for this task is difficult due to the variability and sparsity of whale calls in passive acoustic monitoring datasets. These difficulties are further amplified by time-varying noise that can mask whale calls and by site-specific ambient sound characteristics to which a trained model may not generalize. In this work, we present NAVE, a Conformer-based detector that improves whale-call detection via three components. First, its input representation combines per-bin complex mean subtraction, which suppresses constant site-specific ambient sound characteristics, with an additional per-channel energy normalization (PCEN) channel that adapts to temporal variations in the noise floor. Second, a frequency-dynamic stem processes these noise-aware representations with convolutions that adapt across the characteristic frequency bands of the target call types. Third, we use a Conformer backbone with a convolution kernel matched to the duration of the target calls that adds an inductive bias and improves temporal localization. We evaluate NAVE on BioDCASE 2026 Task 2 using leave-one-site-out cross-validation across the validation sites, which approximates deployment on unseen recording sites. A single NAVE model with a tuned per-class threshold exceeds the stronger WhaleVAD-BPN baseline, using no boundary-proposal network and no search over post-processing parameters. A controlled ablation study shows that the normalized front-end and a duration-matched convolutional kernel each contribute substantially to recovering the D downsweep, the hardest class for previous detectors, with the wide kernel giving the largest aggregate gain.