--- title: "Interspeech 2025 — accepted papers — Elamur Research" description: "Interspeech 2025 — accepted papers: 5 papers in the Elamur Research library, with our summaries, ranked by citations." canonical: "https://research.elamur.ai/free/en/venues/interspeech-usb/2025/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/interspeech-usb/2025/) [home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/) / 2025 # Interspeech 2025 — accepted papers Interspeech 2025 is the 2025 edition of the Interspeech. OpenAlex lists 1,151 papers of it; our library holds 5 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions. [**1,151** papers in the proceedings](#all) · [**5** works in our library](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2025/#works) · [**43** citations of these works](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2025/#works) ## Most cited papers By their OpenAlex citations; a paper with our summary links to its page here, the others to the original. 1. **[Automatic Speech Recognition Biases in Newcastle English: an Error Analysis ↗](https://doi.org/10.21437/interspeech.2025-1973)**Dana Serditova, Kevin Tang, Jochen Steffens*23 citations* 2. **[Interspeech 2025 URGENT Speech Enhancement Challenge ↗](https://doi.org/10.21437/interspeech.2025-1363)**Kohei Saijo, Wangyou Zhang, Samuele Cornell et al.*17 citations* 3. **[EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer ↗](https://doi.org/10.21437/interspeech.2025-1137)**Jiarui Hai, Yong Peng Xu, Hao Zhang et al.*13 citations* 4. **[Replay Attacks Against Audio Deepfake Detection ↗](https://doi.org/10.21437/interspeech.2025-20)**Nicolas M. Müller, Piotr Kawa, Wei Herng Choong et al.*12 citations* 5. **[TS3-Codec: Transformer-Based Simple Streaming Single Codec ↗](https://doi.org/10.21437/interspeech.2025-921)**Haibin Wu, Naoyuki Kanda, Şefik Emre Eskimez et al.*9 citations* 6. **[Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization ↗](https://doi.org/10.21437/interspeech.2025-484)**Jiangyu Han, Federico Landini, Johan Rohdin et al.*8 citations* 7. **[Private kNN-VC: Interpretable Anonymization of Converted Speech ↗](https://doi.org/10.21437/interspeech.2025-820)**Carlos Franzreb, Arnab Das, Tim Polzehl et al.*8 citations* 8. **[Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models ↗](https://doi.org/10.21437/interspeech.2025-1411)**Tuan Dat Phuong, Long-Vu Hoang, Huy Dat Tran*8 citations* 9. **[SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information ↗](https://doi.org/10.21437/interspeech.2025-839)**Chih-Kai Yang, Neo Ho, Yen-Ting Piao et al.*8 citations* 10. **[Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models ↗](https://doi.org/10.21437/interspeech.2025-619)**Ke-Han Lu, Chun-Yi Kuan, Hung-yi Lee*8 citations* ## All accepted papers (1,151) The most cited first; 5 with our summary link to their page here, the others to the original. 1. **[Automatic Speech Recognition Biases in Newcastle English: an Error Analysis ↗](https://doi.org/10.21437/interspeech.2025-1973)**Dana Serditova, Kevin Tang, Jochen Steffens*23 citations* 2. **[Interspeech 2025 URGENT Speech Enhancement Challenge ↗](https://doi.org/10.21437/interspeech.2025-1363)**Kohei Saijo, Wangyou Zhang, Samuele Cornell et al.*17 citations* 3. **[EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer ↗](https://doi.org/10.21437/interspeech.2025-1137)**Jiarui Hai, Yong Peng Xu, Hao Zhang et al.*13 citations* 4. **[Replay Attacks Against Audio Deepfake Detection ↗](https://doi.org/10.21437/interspeech.2025-20)**Nicolas M. Müller, Piotr Kawa, Wei Herng Choong et al.*12 citations* 5. **[TS3-Codec: Transformer-Based Simple Streaming Single Codec ↗](https://doi.org/10.21437/interspeech.2025-921)**Haibin Wu, Naoyuki Kanda, Şefik Emre Eskimez et al.*9 citations* 6. **[Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization ↗](https://doi.org/10.21437/interspeech.2025-484)**Jiangyu Han, Federico Landini, Johan Rohdin et al.*8 citations* 7. **[Private kNN-VC: Interpretable Anonymization of Converted Speech ↗](https://doi.org/10.21437/interspeech.2025-820)**Carlos Franzreb, Arnab Das, Tim Polzehl et al.*8 citations* 8. **[Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models ↗](https://doi.org/10.21437/interspeech.2025-1411)**Tuan Dat Phuong, Long-Vu Hoang, Huy Dat Tran*8 citations* 9. **[SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information ↗](https://doi.org/10.21437/interspeech.2025-839)**Chih-Kai Yang, Neo Ho, Yen-Ting Piao et al.*8 citations* 10. **[Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models ↗](https://doi.org/10.21437/interspeech.2025-619)**Ke-Han Lu, Chun-Yi Kuan, Hung-yi Lee*8 citations* 11. **[The Interspeech 2025 Challenge on Speech Emotion Recognition in Naturalistic Conditions ↗](https://doi.org/10.21437/interspeech.2025-1972)**Abinay Reddy Naini, Lucas Goncalves, Ali N. Salman et al.*8 citations* 12. **[Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model ↗](https://doi.org/10.21437/interspeech.2025-874)**Ke Hu, Ehsan Hosseini-Asl, Chen Chen et al.*7 citations* 13. **[Finding the Human Voice in AI: Insights on the Perception of AI-Voice Clones from Naturalness and Similarity Ratings ↗](https://doi.org/10.21437/interspeech.2025-947)**Linda Bakkouche, Charles McGhee, Emily Lau et al.*7 citations* 14. **[FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching ↗](https://doi.org/10.21437/interspeech.2025-1745)**Ziqian Wang, Zikai Liu, Xinfa Zhu et al.*7 citations* 15. **[Lessons Learned from the URGENT 2024 Speech Enhancement Challenge ↗](https://doi.org/10.21437/interspeech.2025-1246)**Wangyou Zhang, Kohei Saijo, Samuele Cornell et al.*7 citations* 16. **[Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition ↗](https://doi.org/10.21437/interspeech.2025-775)**Raphaël Bagat, Irina Illina, Emmanuel Vincent A*7 citations* 17. **[OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning ↗](https://doi.org/10.21437/interspeech.2025-1062)**Yifan Peng, Muhammad Shakeel, Yui Sudo et al.*7 citations* 18. **[RELATE: Subjective evaluation dataset for automatic evaluation of relevance between text and audio ↗](https://doi.org/10.21437/interspeech.2025-1830)**Yusuke Kanamori, Yuki Okamoto, T. Takano et al.*7 citations* 19. **[SHEET: A Multi-purpose Open-source Speech Human Evaluation Estimation Toolkit ↗](https://doi.org/10.21437/interspeech.2025-1977)**Wen-Chin Huang, Erica Cooper, Tomoki Toda*7 citations* 20. **[Self-Improvement for Audio Large Language Model using Unlabeled Speech ↗](https://doi.org/10.21437/interspeech.2025-1200)**Shaowen Wang, Xinyuan Chen, Yao Xu*7 citations* 21. **[TF-Mamba: A Time-Frequency Network for Sound Source Localization ↗](https://doi.org/10.21437/interspeech.2025-9)**Yang Xiao, Rohan Kumar Das*7 citations* 22. **[Unmasking real-world audio deepfakes: A data-centric approach ↗](https://doi.org/10.21437/interspeech.2025-100)**David Combei, Adriana Stan, Dan Oneaţă et al.*7 citations* 23. **[xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2025-108)**Nikolai Lund Kühne, Jan Stubbe Østergaard, Jesper Jensen et al.*7 citations* 24. **[A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs? ↗](https://doi.org/10.21437/interspeech.2025-1530)**Yigitcan Özer, Woosung Choi, Joan Serrà et al.*6 citations* 25. **[Attention-Free Dual-Mode ASR with Latency-Controlled Selective State Spaces ↗](https://doi.org/10.21437/interspeech.2025-1079)**Takafumi Moriya, Masato Mimura, Kiyoaki Matsui et al.*6 citations* [See all 1,151 papers in Interspeech 2025 — accepted papers →](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2025/papers/) ## Papers with our summary in our library (5) The most cited first (OpenAlex citations plus our library's). 1. **[ADI-20: Arabic Dialect Identification dataset and models](https://md.research.elamur.ai/free/en/papers/elleuch-2025-adi-20-arabic-dialect-identification/) [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)**Haroun Elleuch, Salima Mdhaffar, Yannick Esteve, et al.*2025 · 13 citations* 2. **[Towards a Unified Benchmark for Arabic Pronunciation Assessment: Quranic Recitation as Case Study](https://md.research.elamur.ai/free/en/papers/kheir-2025-towards-unified-benchmark-arabic-pronunciation/) [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)**Yassine El Kheir, Omnia Ibrahim, Amit Meghanani, et al.*2025 · 13 citations* 3. **[Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification](https://md.research.elamur.ai/free/en/papers/abdullah-2025-voice-conversion-improves-cross-domain/) [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)**Badr M. Abdullah, Matthew Baas, Bernd Mobius, et al.*2025 · 7 citations* 4. **[ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis](https://md.research.elamur.ai/free/en/papers/toyin-2025-arvoice-multi-speaker-dataset-arabic/) [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)**Hawau Olamide Toyin, Rufael Marew, Humaid Alblooshi, et al.*2025 · 6 citations* 5. **[Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning](https://md.research.elamur.ai/free/en/papers/ozyilmaz-2025-overcoming-data-scarcity-multi-dialectal/) [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)**Omer Tarik Ozyilmaz, Matt Coler, Matias Valdenegro-Toro*2025 · 4 citations* ## Top topics Topics of its works in our library, with the number of works on each. [Semitic languages (5)](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · [Speech & spoken language (2)](https://md.research.elamur.ai/free/en/topics/speech/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) ## Fields [Arts and Humanities (5)](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science (5)](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Psychology (1)](https://md.research.elamur.ai/free/en/shelves/psychology/) · [Social Sciences (1)](https://md.research.elamur.ai/free/en/shelves/social-sciences/) ## Top authors Authors with a page who published here most often: their works here, and the citations of those works. [🧑‍🔬**Salima Mdhaffar**2 works here · 26 citations](https://md.research.elamur.ai/free/en/authors/salima-mdhaffar/) · [🧑‍🔬**Hawau Olamide Toyin**2 works here · 19 citations](https://md.research.elamur.ai/free/en/authors/hawau-olamide-toyin/) · [🧑‍🔬**Amit Meghanani**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/amit-meghanani/) · [🧑‍🔬**Fethi Bougares**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/fethi-bougares/) · [🧑‍🔬**Haroun Elleuch**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/haroun-elleuch/) · [🧑‍🔬**Nada Almarwani**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/nada-almarwani/) · [🧑‍🔬**Omnia Ibrahim**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/omnia-ibrahim/) · [🧑‍🔬**Thomas Hain**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/thomas-hain/) · [🧑‍🔬**Yannick Estève**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/yannick-esteve/) · [🧑‍🔬**Yassine El Kheir**1 work here · 13 citations](https://md.research.elamur.ai/free/en/authors/yassine-el-kheir/) · [🧑‍🔬**Dietrich Klakow**1 work here · 7 citations](https://md.research.elamur.ai/free/en/authors/dietrich-klakow/) · [🧑‍🔬**Hanan Aldarmaki**1 work here · 6 citations](https://md.research.elamur.ai/free/en/authors/hanan-aldarmaki/) works and citations from OpenAlex and our library. - [← previous Interspeech 2024](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2024/) - [↑ back to Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/)