Elamur Research⌕
☰
home / venues / Interspeech / 2021 / papers

Interspeech 2021: all accepted papers

963 papers · page 1 of 10 · the most cited first · ← Interspeech 2021

1 2 … 10

  1. AST: Audio Spectrogram TransformerYuan Gong, Yu-An Chung, James Glass1,086 citations
  2. SUPERB: Speech Processing Universal PERformance BenchmarkShu-Wen Yang, Po-Han Chi, Yung-Sung Chuang et al.666 citations
  3. Unsupervised Cross-Lingual Representation Learning for Speech RecognitionAlexis Conneau, Alexei Baevski, Ronan Collobert et al.606 citations
  4. Emotion Recognition from Speech Using wav2vec 2.0 EmbeddingsLeonardo Pepino, Pablo Riera, Luciana Ferrer378 citations
  5. NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced DatasetsGabriel Mittag, Babak Naderi, Assmaa Chehadi et al.271 citations
  6. WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition ToolkitZhuoyuan Yao, Di Wu, Xiong Wang et al.234 citations
  7. GigaSpeech: An Evolving, Multi-Domain ASR Corpus with 10,000 Hours of Transcribed AudioGuoguo Chen, Shuzhou Chai, Guanbo Wang et al.229 citations
  8. Speech Resynthesis from Discrete Disentangled Self-Supervised RepresentationsAdam Polyak, Yossi Adi, Jade Copet et al.211 citations
  9. MetricGAN+: An Improved Version of MetricGAN for Speech EnhancementSzu‐Wei Fu, Cheng Yu, Tsun-An Hsieh et al.207 citations
  10. Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-TrainingWei-Ning Hsu, Anuroop Sriram, Alexei Baevski et al.182 citations
  11. INTERSPEECH 2021 Deep Noise Suppression ChallengeChandan K. A. Reddy, Harishchandra Dubey, Kazuhito Koishida et al.170 citations
  12. AISHELL-3: A Multi-Speaker Mandarin TTS CorpusYao Shi, Hui Bu, Xin Xu et al.160 citations
  13. Exploring wav2vec 2.0 on Speaker Verification and Language IdentificationZhiyun Fan, Meng Li, Shiyu Zhou et al.154 citations
  14. Keyword Transformer: A Self-Attention Model for Keyword SpottingAxel Berg, Mark O’Connor, Miguel Tairum Cruz147 citations
  15. End-To-End Speaker Segmentation for Overlap-Aware ResegmentationHervé Bredin, Antoine Laurent141 citations
  16. Detecting Cognitive Decline Using Speech Only: The ADReSSo ChallengeSaturnino F. Luz, Fasih Haider, Sofia de la Fuente et al.135 citations
  17. The Third DIHARD Diarization ChallengeNeville Ryant, Prachi Singh, Venkat Krishnamohan et al.132 citations
  18. A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech DetectionXin Wang, Junichi Yamagishi128 citations
  19. VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice ConversionDisong Wang, Liqun Deng, Yu Ting Yeung et al.118 citations
  20. Diff-TTS: A Denoising Diffusion Model for Text-to-SpeechMyeonghun Jeong, Hyeongju Kim, Sung Jun Cheon et al.116 citations
  21. SE-Conformer: Time-Domain Speech Enhancement Using ConformerEesung Kim, Hyeji Seo116 citations
  22. Broadcasted Residual Learning for Efficient Keyword SpottingByeonggeun Kim, Simyung Chang, Jinkyu Lee et al.110 citations
  23. The Multilingual TEDx Corpus for Speech Recognition and TranslationElizabeth Salesky, Matthew Wiesner, Jacob Bremerman et al.110 citations
  24. CoVoST 2 and Massively Multilingual Speech TranslationChanghan Wang, Anne Wu, Jiatao Gu et al.109 citations
  25. UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform GenerationWon Jang, Dan Lim, Jaesam Yoon et al.109 citations
  26. Speech Emotion Recognition with Multi-Task LearningXingyu Cai, Jiahong Yuan, Renjie Zheng et al.108 citations
  27. AVLnet: Learning Audio-Visual Language Representations from Instructional VideosAndrew Rouditchenko, Angie Boggust, David F. Harwath et al.106 citations
  28. DiCOVA Challenge: Dataset, Task, and Baseline System for COVID-19 Diagnosis Using AcousticsAnanya Muguli, Lancelot Pinto, R Nirmala et al.101 citations
  29. ECAPA-TDNN Embeddings for Speaker DiarizationNauman Dawalatabad, Mirco Ravanelli, François Grondin et al.95 citations
  30. DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech EnhancementXiaohuai Le, Hongsheng Chen, Kai Chen et al.92 citations
  31. MUCS 2021: Multilingual and Code-Switching ASR Challenges for Low Resource Indian LanguagesAnuj Diwan, Rakesh Vaideeswaran, Sanket B. Shah et al.92 citations
  32. The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & PrimatesBjörn Wolfgang Schuller, Anton M. Batliner, Christian Bergler et al.89 citations
  33. DCCRN+: Channel-Wise Subband DCCRN with SNR Estimation for Speech EnhancementShubo Lv, Yanxin Hu, Shimin Zhang et al.88 citations
  34. SC-GlowTTS: An Efficient Zero-Shot Multi-Speaker Text-To-Speech ModelEdresson Casanova, Christopher Shulby, Eren Gölge et al.83 citations
  35. PQK: Model Compression via Pruning, Quantization, and Knowledge DistillationJangho Kim, Simyung Chang, Nojun Kwak81 citations
  36. StarGANv2-VC: A Diverse, Unsupervised, Non-Parallel Framework for Natural-Sounding Voice ConversionYinghao Aaron Li, Ali Zare, Nima Mesgarani81 citations
  37. Half-Truth: A Partially Fake Audio Detection DatasetJiangyan Yi, Ye Bai, Jianhua Tao et al.80 citations
  38. The Effect of Silence and Dual-Band Fusion in Anti-Spoofing SystemYuxiang Zhang, Wenchao Wang, Pengyuan Zhang78 citations
  39. AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference ScenarioYihui Fu, Luyao Cheng, Shubo Lv et al.77 citations
  40. Speaker Anonymisation Using the McAdams CoefficientJose Patino, Natalia Tomashenko, Massimiliano Todisco et al.76 citations
  41. Non-Autoregressive Predictive Coding for Learning Speech Representations from Local DependenciesAlexander H. Liu, Yu-An Chung, James Glass75 citations
  42. Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration ModelingIsaac Elias, Heiga Zen, Jonathan Shen et al.74 citations
  43. Automatic Speech Recognition of Disordered Speech: Personalized Models Outperforming Human Listeners on Short PhrasesJordan R. Green, Robert L. MacDonald, Pan-Pan Jiang et al.72 citations
  44. Channel-Wise Gated Res2Net: Towards Robust Detection of Synthetic Speech AttacksXu Li, Xixin Wu, Hui Lu et al.72 citations
  45. Disordered Speech Data Collection: Lessons Learned at 1 Million Utterances from Project EuphoniaRobert L. MacDonald, Pan-Pan Jiang, Julie Cattiau et al.72 citations
  46. Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow FusionDuc Le, Mahaveer Jain, Gil Keren et al.70 citations
  47. Hi-Fi Multi-Speaker English TTS DatasetEvelina Bakhturina, Vitaly Lavrukhin, Boris Ginsburg et al.69 citations
  48. A Simultaneous Denoising and Dereverberation Framework with Target DecouplingAndong Li, Wenzhe Liu, Xiaoxue Luo et al.68 citations
  49. Graph Attention Networks for Anti-SpoofingHemlata Tak, Jee-weon Jung, Jose Patino et al.68 citations
  50. Relaxing the Conditional Independence Assumption of CTC-Based ASR by Conditioning on Intermediate PredictionsJumon Nozaki, Tatsuya Komatsu67 citations
  51. speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation AssessmentJunbo Zhang, Zhiwen Zhang, Yongqing Wang et al.65 citations · our summary
  52. NU-Wave: A Diffusion Probabilistic Model for Neural Audio UpsamplingJunhyeok Lee, Seungu Han62 citations
  53. Clarity-2021 Challenges: Machine Learning Challenges for Advancing Hearing Aid ProcessingSimone Graetzer, Jon Barker, Trevor J. Cox et al.61 citations
  54. PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTSJia Ye, Heiga Zen, Jonathan Shen et al.61 citations
  55. Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation LearningDongwei Jiang, Wubo Li, Miao Yan Cao et al.61 citations
  56. Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource ScenariosRaghavendra Reddy Pappagari, Jaejin Cho, Sonal Joshi et al.60 citations
  57. Advances in Integration of End-to-End Neural and Clustering-Based Diarization for Real Conversational SpeechKeisuke Kinoshita, Marc Delcroix, Naohiro Tawara59 citations
  58. Integrating Frequency Translational Invariance in TDNNs and Frequency Positional Information in 2D ResNets to Enhance Speaker VerificationJenthe Thienpondt, Brecht Desplanques, Kris Demuynck59 citations
  59. Improving Perceptual Quality by Phone-Fortified Perceptual Loss Using Wasserstein Distance for Speech EnhancementTsun-An Hsieh, Cheng Yu, Szu‐Wei Fu et al.58 citations
  60. Alzheimer’s Dementia Recognition Using Acoustic, Lexical, Disfluency and Speech Pause Features Robust to Noisy InputsMorteza Rohanian, Julian Hough, Matthew Purver56 citations
  61. End-to-End Speech Translation via Cross-Modal Progressive TrainingRong Ye, Mingxuan Wang, Lei Li54 citations
  62. Rethinking Evaluation in ASR: Are Our Models Robust Enough?Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap et al.54 citations
  63. Using the Outputs of Different Automatic Speech Recognition Paradigms for Acoustic- and BERT-Based Alzheimer’s Dementia Detection Through Spontaneous SpeechYilin Pan, Bahman Mirheidari, Jennifer Harris et al.54 citations
  64. WavBERT: Exploiting Semantic and Non-Semantic Speech Using Wav2vec and BERT for Dementia DetectionYouxiang Zhu, Abdelrahman Obyat, Xiaohui Liang et al.52 citations
  65. S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained RepresentationsJheng-Hao Lin, Yist Y. Lin, Chung-Ming Chien et al.49 citations
  66. SpecMix : A Mixed Sample Data Augmentation Method for Training with Time-Frequency Domain FeaturesGwantae Kim, David K. Han, Hanseok Ko49 citations
  67. Utilizing Self-Supervised Representations for MOS PredictionWei-Cheng Tseng, Chien‐Yu Huang, Wei-Tsung Kao et al.49 citations
  68. Audio Retrieval with Natural Language QueriesAndreea-Maria Oncescu, A. Sophia Koepke, João F. Henriques et al.48 citations
  69. Towards the Explainability of Multimodal Speech Emotion RecognitionPuneet Kumar, Vishesh Kaushik, Balasubramanian Raman48 citations
  70. Explore wav2vec 2.0 for Mispronunciation DetectionXiaoshuo Xu, Yueteng Kang, Songjun Cao et al.46 citations
  71. INTERSPEECH 2021 Acoustic Echo Cancellation ChallengeRoss Cutler, Ando Saabas, Tanel Pärnamaa et al.46 citations
  72. Fre-GAN: Adversarial Frequency-Consistent Audio SynthesisJi-Hoon Kim, Sanghoon Lee, Ji-Hyun Lee et al.45 citations
  73. LiRA: Learning Visual Speech Representations from Audio Through Self-SupervisionPingchuan Ma, Rodrigo Mira, Stavros Petridis et al.45 citations
  74. Transformer Based End-to-End Mispronunciation Detection and DiagnosisMinglin Wu, Kun Li, Wai-Kim Leung et al.45 citations
  75. slimIPL: Language-Model-Free Iterative Pseudo-LabelingTatiana Likhomanenko, Qiantong Xu, Jacob Kahn et al.45 citations
  76. An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word ModelingTara N. Sainath, Yanzhang He, Arun Narayanan et al.44 citations
  77. IR-GAN: Room Impulse Response Generator for Far-Field Speech RecognitionAnton Jeran Ratnarajah, Zhenyu Tang, Dinesh Manocha44 citations
  78. WaveGrad 2: Iterative Refinement for Text-to-Speech SynthesisNanxin Chen, Yu Zhang, Heiga Zen et al.44 citations
  79. A Study on Fine-Tuning wav2vec2.0 Model for the Task of Mispronunciation Detection and DiagnosisLinkai Peng, Kaiqi Fu, Binghuai Lin et al.43 citations
  80. Alzheimer Disease Recognition Using Speech-Based Embeddings From Pre-Trained ModelsLara Gauder, Leonardo Pepino, Luciana Ferrer et al.43 citations
  81. Automatic Detection of Alzheimer’s Disease Using Spontaneous Speech OnlyJun Chen, Jieping Ye, Fengyi Tang et al.43 citations
  82. Speech Denoising Without Clean Training Data: A Noise2Noise ApproachMadhav Mahesh Kashyap, Anuj Tambwekar, K M Manohara et al.43 citations
  83. The Energy and Carbon Footprint of Training End-to-End Speech RecognizersTitouan Parcollet, Mirco Ravanelli43 citations
  84. wav2vec-C: A Self-Supervised Model for Speech Representation LearningSamik Sadhu, Di He, Che-Wei Huang et al.43 citations
  85. Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech RecognitionGenta Indra Winata, Guangsen Wang, Caiming Xiong et al.42 citations
  86. On the Limit of English Conversational Speech RecognitionZoltán Tüske, George Saon, Brian E. D. Kingsbury41 citations · our summary
  87. Siamese Network with wav2vec Feature for Spoofing Speech DetectionYang Xie, Zhenchuan Zhang, Yingchun Yang41 citations
  88. An Initial Investigation for Detecting Partially Spoofed AudioLin Zhang, Xin Wang, Erica Cooper et al.40 citations
  89. Earnings-21: A Practical Benchmark for ASR in the WildMiguel Del Rio, Natalie Delworth, Ryan Westerman et al.39 citations
  90. Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion DiscriminabilityRui Liu, Berrak Şişman, Haizhou Li39 citations
  91. The Zero Resource Speech Challenge 2021: Spoken Language ModellingEwan Dunbar, Mathieu Bernard, Nicolas Hamilakis et al.39 citations
  92. Generalized Spatio-Temporal RNN Beamformer for Target Speech SeparationYong Xu, Zhuohuang Zhang, Meng Yu et al.38 citations
  93. Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR ModelsMohammad Zeineldeen, Глушко Андрей Владимирович, Wilfried Michel et al.38 citations
  94. Adversarial Data Augmentation for Disordered Speech RecognitionZengrui Jin, Mengzhe Geng, Xurong Xie et al.37 citations
  95. Comparing Acoustic-Based Approaches for Alzheimer’s Disease DetectionAparna Balagopalan, Jekaterina Novikova37 citations
  96. F-T-LSTM Based Complex Network for Joint Acoustic Echo Cancellation and Speech EnhancementShimin Zhang, Yuxiang Kong, Shubo Lv et al.37 citations
  97. Learning Fine-Grained Cross Modality Excitement for Speech Emotion RecognitionHang Li, Wenbiao Ding, Zhongqin Wu et al.37 citations
  98. SynthASR: Unlocking Synthetic Data for Speech RecognitionAmin Fazel, Wei Yang, Yulan Liu et al.37 citations
  99. Few-Shot Keyword Spotting in Any LanguageMark Mazumder, Colby Banbury, Josh Meyer et al.36 citations
  100. RW-Resnet: A Novel Speech Anti-Spoofing Model Using Raw WaveformYouxuan Ma, Zongze Ren, Shugong Xu36 citations

1 2 … 10

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/