Synthetic Data Augmentation for Speech Recognition

Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 16

All topics
CardsList

  1. Foreground Voice Activity Detection: Learning Speaker Selectivity from Supervision

    Sep 17, 2026Guangzhao Yang, Muhammad Huzaifah, Yu Pan +2Data AugmentationSpeech Processing

    R&D Team, Recho Inc., Tokyo, Japan

  2. ConversationalVoice: Full-Duplex Speech Data from Real Conversations through Source-Faithful Reconstruction and Conversation-Grounded Expansion

    Sep 8, 2026Richard Yucheng He, Baodong Cao, Chen Xu +2TTS SynthesisData Augmentation

    AveraLabs

  3. Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation

    Aug 27, 2026Zhen Wang, TianRui Wu, RongQi Han +3Synthetic Data AugmentationTTS Synthesis

    Shanghai Qi Zhi Institute, Shanghai, China · Megatronix (Beijing) Technology Co., Ltd. · Tsinghua University, Beijing, China

  4. On the Role of Conversational Timing in Synthetic Training Data for ASR

    Jul 9, 2026Máté Gedeon, Péter MihajlikAutomatic Speech RecognitionSynthetic Data Augmentation for Speech Recognition

    Dept. of Telecommunications and Artificial Intelligence, Budapest University of Technology and Economics, Hungary · Speechtex Ltd.

  5. LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering

    Jul 2, 2026Nina Hosseini-Kivanani, Marco Matassoni, Alessio BruttiSpoken Language UnderstandingSynthetic Data Augmentation

    Radio Télévisioun Lëtzebuerg (RTL) · University of Luxembourg · Fondazione Bruno Kessler (FBK)

  6. How to Leverage Synthetic Speech for LLM-Based ASR Systems?

    Jun 27, 2026Yanis Labrak, Dairazalia Sanchez-Cortes, Sergio Burdisso +9Synthetic-to-Real Domain AdaptationSynthetic Data Augmentation

    Idiap Research Institute, Martigny, Switzerland · Universite de Toulon, Aix Marseille Univ, LIS, CNRS, Toulon, France · EPFL, Lausanne, Switzerland +3

  7. DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation

    Jun 19, 2026Yao LuSynthetic Data AugmentationTTS Synthesis

    TMCC, College of Computer Science, Nankai University, Tianjin, China

  8. Synthetic Audio Generation Framework for Air Traffic Control Speech Recognition

    Jun 19, 2026Raphaël Bagat, Zhe Zhang, Junichi Yamagishi +2Synthetic Data GenerationSpeech Processing

    Universit´e de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France · National Institute of Informatics, Tokyo, Japan

  9. Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning

    Jun 18, 2026Satwinder Singh, Qianli Wang, Zihan Zhong +4Synthetic Data AugmentationAutomatic Speech Recognition

    DeepNet Discovery Network, University of Auckland, New Zealand · University of Illinois Urbana-Champaign, USA

  10. Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation

    Jun 18, 2026Paban Sapkota, Hemant Kumar Kathania, Sudarsana Reddy Kadiri +1Data AugmentationAutomatic Speech Recognition

    Department of Electronics and Communication Engineering, National Institute of Technology Sikkim, India · Signal Analysis and Interpretation Laboratory (SAIL), University of Southern California, Los Angeles, USA

  11. Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation

    Jun 17, 2026Fan Xu, Yangjie Dan, Keyu Yan +2Speech ProcessingSynthetic Data Augmentation for Speech Recognition

    Jiangxi Normal University, China

  12. Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech

    Jun 14, 2026Yue Heng Yeo, Haoyang Li, Yizhou Peng +6Code-Switching Speech RecognitionSynthetic Data Augmentation

    College of Computing and Data Science, Nanyang Technological University, Singapore · HLT-COE & CLSP, Johns Hopkins University, USA · Institute for Infocomm Research (I2R), A⋆STAR, Singapore +1

  13. Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026

    Jun 3, 2026Enes Yavuz Ugan, Maike Züfle, Yuka Ko +5MBR DecodingInstruction Following

    1Karlsruhe Institute of Technology · 2Carnegie Mellon University

  14. Efficient ASR Training with Conversations that Never Happened

    Jun 2, 2026Máté Gedeon, Péter MihajlikSynthetic Data AugmentationAutomatic Speech Recognition

    Dept. of Telecommunications and Artificial Intelligence, Budapest University of Technology and Economics, Budapest, Hungary · SpeechTex Ltd., Budapest, Hungary · ELTE Research Centre for Linguistics, Budapest, Hungary

  15. The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

    May 4, 2026Venkata Pushpak Teja MentaCode-Switching Speech RecognitionASR Evaluation

    Praxel Ventures

  16. Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

    Apr 30, 2026Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson +2Synthetic-to-Real Domain AdaptationSynthetic Data Augmentation

    University of Illinois Urbana-Champaign, USA · National Center for Supercomputing Applications, USA