method · first seen 6 Oct 2026
connectionist temporal classification
Also: CTC
A loss function for training sequence models without frame-level alignments, commonly used in speech recognition.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMsPapers · 6 Oct 2026 · Hemant Yadav, Sunayana Sitaram, Roger Zimmermann, Rajiv Ratn Shah
- Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented LanguagesPapers · 7 Oct 2026 · Muhammad Huzaifah, Yu Pan, Zachary Yeo, Ningjie Bai, Guangzhao Yang
- Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain StudyPapers · 8 Oct 2026 · Christopher Witzl, Tobias Bocklet, Korbinian Riedhammer
- 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 Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing ImageryPapers · 12 Oct 2026 · Zhongyu Pang
- FirmwareVersion/choravoxCode · 14 Oct 2026 · FirmwareVersion · 33 stars
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
- TID System for Speech-COSER Challenge 2026: ASR TrackPapers · 8 Nov 2026 · Fernando López, Jordi Luque
- LipLingo: CNN Model for Lip ReadingPapers · 2 Nov 2026 · Mahmoud S. Mayaleh, Liban Ali Achkir, Nijat Mehdiyev, Ahmet Ozdil
- Reading-Level Verification of Kanji Words in Japanese Financial Speech SynthesisPapers · 29 Oct 2026 · Cheng Zhang
- A Systematic Comparison of Search Space Complexity and Efficiency for Time-Synchronous End-to-End ASR ModelsPapers · 22 Oct 2026 · Simon Berger, Larissa Kleppel, Ralf Schlüter
- Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysisPapers · 20 Oct 2026 · Mohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain, Farzana Akter, AKM Bahal…
- How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented EncoderPapers · 18 Oct 2026 · Amr Abdelkhalik
- From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource ScriptsPapers · 18 Oct 2026 · Faizan Iqbal, Haq Nawaz Malik, Hafsah Pervaiz
- FirmwareVersion/choravoxCode · 14 Oct 2026 · FirmwareVersion · 33 stars
- From Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing ImageryPapers · 12 Oct 2026 · Zhongyu Pang
- 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
- Phonologically Informed Tokenization for German Speech Recognition: A Cross-Domain StudyPapers · 8 Oct 2026 · Christopher Witzl, Tobias Bocklet, Korbinian Riedhammer