📰 Interspeech 2022 — accepted papers

Interspeech 2022 is the 2022 edition of the Interspeech. OpenAlex lists 1,102 papers of it; our library holds 4 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at ScaleArun Babu, Changhan Wang, Andros Tjandra et al.553 citations · our summary
2. UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022Takaaki Saeki, Detai Xin, Wataru Nakata et al.244 citations
3. Does Audio Deepfake Detection Generalize?Nicolas Müller, Pavel Czempin, Franziska Diekmann et al.243 citations
4. Efficient Training of Audio Transformers with PatchoutKhaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh et al.225 citations
5. MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker VerificationYang Zhang, Zhiqiang Lv, Haibin Wu et al.132 citations
6. CMGAN: Conformer-based Metric GAN for Speech EnhancementRuizhe Cao, Sherif Abdulatif, Bin Yang118 citations
7. Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech RecognitionZhifu Gao, Shiliang Zhang, Ian Vince McLoughlin et al.116 citations
8. Robust Self-Supervised Audio-Visual Speech RecognitionBowen Shi, Wei-Ning Hsu, Abdelrahman Mohamed102 citations
9. WeNet 2.0: More Productive End-to-End Speech Recognition ToolkitBinbin Zhang, Di Wu, Zhendong Peng et al.101 citations
10. Pushing the limits of raw waveform speaker recognitionJee-weon Jung, Youjin Kim, Hee-Soo Heo et al.95 citations

All accepted papers (1,102)

The most cited first; 4 with our summary link to their page here, the others to the original.

1. XLS-R: Self-supervised Cross-lingual Speech Representation Learning at ScaleArun Babu, Changhan Wang, Andros Tjandra et al.553 citations · our summary
2. UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022Takaaki Saeki, Detai Xin, Wataru Nakata et al.244 citations
3. Does Audio Deepfake Detection Generalize?Nicolas Müller, Pavel Czempin, Franziska Diekmann et al.243 citations
4. Efficient Training of Audio Transformers with PatchoutKhaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh et al.225 citations
5. MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker VerificationYang Zhang, Zhiqiang Lv, Haibin Wu et al.132 citations
6. CMGAN: Conformer-based Metric GAN for Speech EnhancementRuizhe Cao, Sherif Abdulatif, Bin Yang118 citations
7. Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech RecognitionZhifu Gao, Shiliang Zhang, Ian Vince McLoughlin et al.116 citations
8. Robust Self-Supervised Audio-Visual Speech RecognitionBowen Shi, Wei-Ning Hsu, Abdelrahman Mohamed102 citations
9. WeNet 2.0: More Productive End-to-End Speech Recognition ToolkitBinbin Zhang, Di Wu, Zhendong Peng et al.101 citations
10. Pushing the limits of raw waveform speaker recognitionJee-weon Jung, Youjin Kim, Hee-Soo Heo et al.95 citations
11. Speech Enhancement with Score-Based Generative Models in the Complex STFT DomainSimon Welker, Julius Richter, Timo Gerkmann94 citations
12. MAE-AST: Masked Autoencoding Audio Spectrogram TransformerAlan Baade, Puyuan Peng, David F. Harwath87 citations
13. Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event DetectionHyeonuk Nam, Seong-Hu Kim, Byeong-Yun Ko et al.84 citations
14. The VoiceMOS Challenge 2022Wen-Chin Huang, Erica Cooper, Yu Tsao et al.81 citations
15. MAESTRO: Matched Speech Text Representations through Modality MatchingZhehuai Chen, Yu Zhang, Andrew Rosenberg et al.74 citations
16. Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice SynthesisYu Wang, Xinsheng Wang, Pengcheng Zhu et al.72 citations
17. How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASRKazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix et al.69 citations
18. SpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of SpeechWeidong Chen, Xiaofen Xing, Xiangmin Xu et al.68 citations
19. Separate What You Describe: Language-Queried Audio Source SeparationXubo Liu, Haohe Liu, Qiuqiang Kong et al.66 citations
20. Simple and Effective Zero-shot Cross-lingual Phoneme RecognitionQiantong Xu, Alexei Baevski, Michael Auli64 citations
21. BARTpho: Pre-trained Sequence-to-Sequence Models for VietnameseNguyen Luong Tran, Duong Le, Dat Quoc Nguyen61 citations
22. Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech RecognitionAbner Hernandez, Paula Andrea Pérez-Toro, Elmar Nöth et al.56 citations
23. Streaming Multi-Talker ASR with Token-Level Serialized Output TrainingNaoyuki Kanda, Jian Wu, Yu Wu et al.56 citations
24. SASV 2022: The First Spoofing-Aware Speaker Verification ChallengeJee-weon Jung, Hemlata Tak, Hye-jin Shim et al.55 citations
25. VoiceFixer: A Unified Framework for High-Fidelity Speech RestorationHaohe Liu, Xubo Liu, Qiuqiang Kong et al.53 citations

See all 1,102 papers in Interspeech 2022 — accepted papers →

📄 Papers with our summary in our library (4)

The most cited first (OpenAlex citations plus our library's).

1. BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language modelBrooke Stephenson, Laurent Besacier, Laurent Girin, et al.2022 · 9 citations
2. Automatic Dialect Density Estimation for African American EnglishAlexander Johnson, Kevin Everson, Vijay Ravi, et al.2022 · 8 citations
3. An Investigation of Indian Native Language Phonemic Influences on L2 English PronunciationsInterspeechShelly Jain, Priyanshi Pal, Anil Vuppala, et al.2022 · 1 citation
4. Representing 'how you say' with 'what you say': English corpus of focused speech and text reflecting corresponding implicationsInterspeechNaoaki Suzuki, Satoshi Nakamura2022 · 1 citation

🧭 Top topics

Topics of its works in our library, with the number of works on each.

English (4)🧠Language models & pretraining (1)

📚 Fields

🎭Arts and Humanities (4)🖥️Computer Science (3)💭Psychology (2)

🧑‍🔬 Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

🏛️ Top institutions

Institutions on the bylines of its works here, by the number of works.

🎓University of California, Los AngelesLos Angeles · United States1 work here🎓University of WashingtonSeattle · United States1 work here🎓Nara Institute of Science and TechnologyIkoma · Japan1 work here

works and citations from OpenAlex and our library.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/interspeech-usb/2022/