architecture · first seen 9 Oct 2026
Conformer
A speech encoder architecture combining convolution and self-attention, often trained with CTC loss.
Mentions per week
PapersCodeDiscussion
Earliest sources
- From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at ScalePapers · 9 Oct 2026 · Yaroslav Getman, Tamás Grósz, Tommi Lehtonen, Mikko Kurimo
- Oído: Real-Time Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural AcceleratorPapers · 9 Oct 2026 · Daniel Varela Sánchez, Guillermo Martín-Coello Juárez
- Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech RecognitionPapers · 13 Oct 2026 · Santosh Dahal, Anmol Guragain, Tianchi Liu, Luis Fernando D'Haro, Kiran Chandra…
- Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian LanguagesPapers · 14 Oct 2026 · Stephen Fernandes, Narayan Choudhary
- Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or HybridPapers · 26 Oct 2026 · Tamas Kovacs, Daniel Luger
- NAVE: A Normalized, Adaptive Conformer for Antarctic Whale Vocalization DetectionPapers · 6 Nov 2026 · Matthias Nagl, Paul Primus, Gerhard Widmer
Latest sources
- Swanada: Split-Encoder Capability-Routed Conformer CTC and Sub-30 MB On-Device Speech Recognition Across Twelve ScriptsPapers · 10 Nov 2026 · Hemanth HM
- NAVE: A Normalized, Adaptive Conformer for Antarctic Whale Vocalization DetectionPapers · 6 Nov 2026 · Matthias Nagl, Paul Primus, Gerhard Widmer
- Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or HybridPapers · 26 Oct 2026 · Tamas Kovacs, Daniel Luger
- Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian LanguagesPapers · 14 Oct 2026 · Stephen Fernandes, Narayan Choudhary
- Mixture of Phonetic Experts Based Low-Rank Adaptation of Conformer Models for Accented English Speech RecognitionPapers · 13 Oct 2026 · Santosh Dahal, Anmol Guragain, Tianchi Liu, Luis Fernando D'Haro, Kiran Chandra…
- Oído: Real-Time Open-Vocabulary Speech Recognition on a $5 Microcontroller without a Neural AcceleratorPapers · 9 Oct 2026 · Daniel Varela Sánchez, Guillermo Martín-Coello Juárez
- From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at ScalePapers · 9 Oct 2026 · Yaroslav Getman, Tamás Grósz, Tommi Lehtonen, Mikko Kurimo