---
title: "IEEE/ACM Transactions on Audio Speech and Language"
description: "All 281 papers of IEEE/ACM Transactions on Audio Speech and Language Processing 2021 · page 1 of 3, the most cited first; those with our…"
canonical: "https://research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [IEEE/ACM Transactions on Audio Speech…](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/) / [2021](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/) / papers

# IEEE/ACM Transactions on Audio Speech and Language Processing 2021: all accepted papers

281 papers · page 1 of 3 · the most cited first · [← IEEE/ACM Transactions on Audio Speech and Language Processing 2021](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/)

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/2/) [3](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/3/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/2/)

1. **[HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://md.research.elamur.ai/free/en/papers/hsu-2021-hubert-self-supervised-speech-representation/)**Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai et al.*2,919 citations · our summary*
2. **[Pre-Training With Whole Word Masking for Chinese BERT](https://md.research.elamur.ai/free/en/papers/cui-2019-pre-training-whole-word-masking/)**Yiming Cui, Wanxiang Che, Ting Liu et al.*1,181 citations · our summary*
3. **[SoundStream: An End-to-End Neural Audio Codec](https://md.research.elamur.ai/free/en/papers/zeghidour-2021-soundstream-end-end-neural-audio/)**Neil Zeghidour, Alejandro Luebs, Ahmed Omran et al.*610 citations · our summary*
4. **[FSD50K: An Open Dataset of Human-Labeled Sound Events ↗](https://doi.org/10.1109/taslp.2021.3133208)**Eduardo Fonseca, Xavier Favory, Jordi Pons et al.*449 citations*
5. **[An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation ↗](https://doi.org/10.1109/taslp.2021.3066303)**Daniel Michelsanti, Zheng‐Hua Tan, Shi-Xiong Zhang et al.*316 citations*
6. **[TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech ↗](https://doi.org/10.1109/taslp.2021.3095662)**Andy T. Liu, Shang-Wen Li, Hung-yi Lee*312 citations*
7. **[CTNet: Conversational Transformer Network for Emotion Recognition ↗](https://doi.org/10.1109/taslp.2021.3049898)**Zheng Lian, Bin Liu, Jianhua Tao*296 citations*
8. **[Wavesplit: End-to-End Speech Separation by Speaker Clustering ↗](https://doi.org/10.1109/taslp.2021.3099291)**Neil Zeghidour, David Grangier*257 citations*
9. **[Two Heads are Better Than One: A Two-Stage Complex Spectral Mapping Approach for Monaural Speech Enhancement ↗](https://doi.org/10.1109/taslp.2021.3079813)**Andong Li, Wenzhe Liu, Chengshi Zheng et al.*192 citations*
10. **[Dense CNN With Self-Attention for Time-Domain Speech Enhancement ↗](https://doi.org/10.1109/taslp.2021.3064421)**Ashutosh Pandey, DeLiang Wang*182 citations*
11. **[PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation ↗](https://doi.org/10.1109/taslp.2021.3120633)**Yuan Gong, Yu-An Chung, James Glass*162 citations*
12. **[The Detection of Parkinson's Disease From Speech Using Voice Source Information ↗](https://doi.org/10.1109/taslp.2021.3078364)**N. P. Narendra, Björn Wolfgang Schuller, Paavo Alku*127 citations*
13. **[FluentNet: End-to-End Detection of Stuttered Speech Disfluencies With Deep Learning ↗](https://doi.org/10.1109/taslp.2021.3110146)**Tedd Kourkounakis, Amirhossein Hajavi, Ali Etemad*109 citations*
14. **[High-Resolution Piano Transcription With Pedals by Regressing Onset and Offset Times ↗](https://doi.org/10.1109/taslp.2021.3121991)**Qiuqiang Kong, Bochen Li, Xuchen Song et al.*109 citations*
15. **[Recent Progress in the CUHK Dysarthric Speech Recognition System ↗](https://doi.org/10.1109/taslp.2021.3091805)**Shansong Liu, Mengzhe Geng, Shoukang Hu et al.*95 citations*
16. **[Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation ↗](https://doi.org/10.1109/taslp.2021.3083405)**Zhong-Qiu Wang, Peidong Wang, DeLiang Wang*90 citations*
17. **[Analyzing Multimodal Sentiment Via Acoustic- and Visual-LSTM With Channel-Aware Temporal Convolution Network ↗](https://doi.org/10.1109/taslp.2021.3068598)**Sijie Mai, Songlong Xing, Haifeng Hu*88 citations*
18. **[Expressive TTS Training With Frame and Style Reconstruction Loss ↗](https://doi.org/10.1109/taslp.2021.3076369)**Rui Liu, Berrak Şişman, Guanglai Gao et al.*85 citations*
19. **[Information Fusion in Attention Networks Using Adaptive and Multi-Level Factorized Bilinear Pooling for Audio-Visual Emotion Recognition ↗](https://doi.org/10.1109/taslp.2021.3096037)**Hengshun Zhou, Jun Du, Yuanyuan Zhang et al.*84 citations*
20. **[Speech Enhancement Using Multi-Stage Self-Attentive Temporal Convolutional Networks ↗](https://doi.org/10.1109/taslp.2021.3125143)**Ju Lin, Adriaan J. van Wijngaarden, Kuang‐Ching Wang et al.*84 citations*
21. **[Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling ↗](https://doi.org/10.1109/taslp.2021.3076867)**Songxiang Liu, Yuewen Cao, Disong Wang et al.*83 citations*
22. **[Towards Model Compression for Deep Learning Based Speech Enhancement ↗](https://doi.org/10.1109/taslp.2021.3082282)**Ke Tan, DeLiang Wang*82 citations*
23. **[Speech Emotion Recognition Considering Nonverbal Vocalization in Affective Conversations ↗](https://doi.org/10.1109/taslp.2021.3076364)**Jia-Hao Hsu, Ming-Hsiang Su, Chung‐Hsien Wu et al.*77 citations*
24. **[Multimodal Emotion Recognition With Temporal and Semantic Consistency ↗](https://doi.org/10.1109/taslp.2021.3129331)**Bingzhi Chen, Qi Zhi Cao, Mi-Xiao Hou et al.*71 citations*
25. **[Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence ↗](https://doi.org/10.1109/taslp.2021.3069302)**Matteo Torcoli, Thorsten Kastner, Jürgen Herre*71 citations*
26. **[Bridging Text and Video: A Universal Multimodal Transformer for Audio-Visual Scene-Aware Dialog ↗](https://doi.org/10.1109/taslp.2021.3065823)**Zekang Li, Zongjia Li, Jinchao Zhang et al.*68 citations*
27. **[Desynchronization Attacks Resilient Watermarking Method Based on Frequency Singular Value Coefficient Modification ↗](https://doi.org/10.1109/taslp.2021.3092555)**Juan Zhao, Tianrui Zong, Yong Xiang et al.*64 citations*
28. **[Exploiting Adapters for Cross-Lingual Low-Resource Speech Recognition ↗](https://doi.org/10.1109/taslp.2021.3138674)**Wenxin Hou, Han Zhu, Yidong Wang et al.*64 citations*
29. **[Multi-Task Sequence Tagging for Emotion-Cause Pair Extraction Via Tag Distribution Refinement ↗](https://doi.org/10.1109/taslp.2021.3089837)**Chuang Fan, Chaofa Yuan, Lin Gui et al.*63 citations*
30. **[A Unified Target-Oriented Sequence-to-Sequence Model for Emotion-Cause Pair Extraction ↗](https://doi.org/10.1109/taslp.2021.3102194)**Zifeng Cheng, Zhiwei Jiang, Yafeng Yin et al.*62 citations*
31. **[Audio-Visual Deep Neural Network for Robust Person Verification ↗](https://doi.org/10.1109/taslp.2021.3057230)**Yanmin Qian, Zhengyang Chen, Shuai Wang*61 citations*
32. **[Towards Robust Speech Super-Resolution ↗](https://doi.org/10.1109/taslp.2021.3054302)**Heming Wang, DeLiang Wang*59 citations*
33. **[Sarcasm Detection with Commonsense Knowledge ↗](https://doi.org/10.1109/taslp.2021.3120601)**Jiangnan Li, Hongliang Pan, Zheng Lin et al.*58 citations*
34. **[Nearest Kronecker Product Decomposition Based Linear-in-The-Parameters Nonlinear Filters ↗](https://doi.org/10.1109/taslp.2021.3084755)**Sankha Subhra Bhattacharjee, Nithin V. George*57 citations*
35. **[Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT ↗](https://doi.org/10.1109/taslp.2021.3082299)**Ye Bai, Jiangyan Yi, Jianhua Tao et al.*55 citations*
36. **[Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks ↗](https://doi.org/10.1109/taslp.2021.3082307)**Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer*54 citations*
37. **[Spatial Active Noise Control Based on Kernel Interpolation of Sound Field ↗](https://doi.org/10.1109/taslp.2021.3107983)**Shoichi Koyama, Jesper Brunnström, Hayato Ito et al.*54 citations*
38. **[Modified Magnitude-Phase Spectrum Information for Spoofing Detection ↗](https://doi.org/10.1109/taslp.2021.3060810)**Jichen Yang, Hongji Wang, Rohan Kumar Das et al.*53 citations*
39. **[On the Robustness of the Superdirective Beamformer ↗](https://doi.org/10.1109/taslp.2021.3053410)**Xi Chen, Jacob Benesty, Gongping Huang et al.*53 citations*
40. **[Towards Duration Robust Weakly Supervised Sound Event Detection ↗](https://doi.org/10.1109/taslp.2021.3054313)**Heinrich Dinkel, Mengyue Wu, Kai Yu*51 citations*
41. **[Zero-Shot Audio Classification Via Semantic Embeddings ↗](https://doi.org/10.1109/taslp.2021.3065234)**Huang Xie, Tuomas I. Virtanen*51 citations*
42. **[Comparison of Feature Extraction Methods for Sound-Based Classification of Honey Bee Activity ↗](https://doi.org/10.1109/taslp.2021.3133194)**Alessandro Terenzi, Nicola Ortolani, Inês Nolasco et al.*50 citations*
43. **[Deep Learning Based Real-Time Speech Enhancement for Dual-Microphone Mobile Phones ↗](https://doi.org/10.1109/taslp.2021.3082318)**Ke Tan, Xueliang Zhang, DeLiang Wang*50 citations*
44. **[Neural Network Adaptation and Data Augmentation for Multi-Speaker Direction-of-Arrival Estimation ↗](https://doi.org/10.1109/taslp.2021.3060257)**Weipeng He, Petr Motlíček, Jean‐Marc Odobez*47 citations*
45. **[DUMA: Reading Comprehension With Transposition Thinking ↗](https://doi.org/10.1109/taslp.2021.3138683)**Pengfei Zhu, Zhuosheng Zhang, Hai Zhao et al.*46 citations*
46. **[High-Order Pair-Wise Aspect and Opinion Terms Extraction With Edge-Enhanced Syntactic Graph Convolution ↗](https://doi.org/10.1109/taslp.2021.3095672)**Shengqiong Wu, Hao Fei, Yafeng Ren et al.*44 citations*
47. **[Pretraining Techniques for Sequence-to-Sequence Voice Conversion ↗](https://doi.org/10.1109/taslp.2021.3049336)**Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu et al.*44 citations*
48. **[Detection of Multiple Steganography Methods in Compressed Speech Based on Code Element Embedding, Bi-LSTM and CNN With Attention Mechanisms ↗](https://doi.org/10.1109/taslp.2021.3074752)**Songbin Li, Jingang Wang, Peng Liu et al.*42 citations*
49. **[LSBert: Lexical Simplification Based on BERT ↗](https://doi.org/10.1109/taslp.2021.3111589)**Jipeng Qiang, Yun Li, Yi Qing Zhu et al.*42 citations*
50. **[Mixed Source Sound Field Translation for Virtual Binaural Application With Perceptual Validation ↗](https://doi.org/10.1109/taslp.2021.3061939)**Lachlan I. Birnie, Thushara Dheemantha Abhayapala, Vladimir Tourbabin et al.*40 citations*
51. **[Binaural Reproduction Based on Bilateral Ambisonics and Ear-Aligned HRTFs ↗](https://doi.org/10.1109/taslp.2021.3055038)**Zamir Ben-Hur, David Lou Alon, Ravish Mehra et al.*39 citations*
52. **[Contrastive Information Extraction With Generative Transformer ↗](https://doi.org/10.1109/taslp.2021.3110126)**Ningyu Zhang, Hongbin Ye, Shumin Deng et al.*39 citations*
53. **[Multi-View Speech Emotion Recognition Via Collective Relation Construction ↗](https://doi.org/10.1109/taslp.2021.3133196)**Mi-Xiao Hou, Zheng Zhang, Qi Zhi Cao et al.*39 citations*
54. **[A Joint Diagonalization Based Efficient Approach to Underdetermined Blind Audio Source Separation Using the Multichannel Wiener Filter ↗](https://doi.org/10.1109/taslp.2021.3079815)**Nobutaka Ito, Rintaro Ikeshita, Hiroshi Sawada et al.*38 citations*
55. **[Robust Q-Gradient Subband Adaptive Filter for Nonlinear Active Noise Control ↗](https://doi.org/10.1109/taslp.2021.3102193)**Kaili Yin, Yi-Fei Pu, Lu Lu*38 citations*
56. **[Speech Emotion Recognition Using Sequential Capsule Networks ↗](https://doi.org/10.1109/taslp.2021.3120586)**Xixin Wu, Yuewen Cao, Hui Lu et al.*38 citations*
57. **[Determined BSS Based on Time-Frequency Masking and Its Application to Harmonic Vector Analysis ↗](https://doi.org/10.1109/taslp.2021.3073863)**Kohei Yatabe, Daichi Kitamura*37 citations*
58. **[Exploiting Temporal Context in CNN Based Multisource DOA Estimation ↗](https://doi.org/10.1109/taslp.2021.3067113)**Alexander Bohlender, Ann Spriet, Wouter Tirry et al.*37 citations*
59. **[Multi-Tone Phase Coding of Interaural Time Difference for Sound Source Localization With Spiking Neural Networks ↗](https://doi.org/10.1109/taslp.2021.3100684)**Zihan Pan, Malu Zhang, Jibin Wu et al.*37 citations*
60. **[Cascaded Random Fourier Filter for Robust Nonlinear Active Noise Control ↗](https://doi.org/10.1109/taslp.2021.3126943)**Yingying Zhu, Haiquan Zhao, Xiaoqiong He et al.*36 citations*
61. **[Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System ↗](https://doi.org/10.1109/taslp.2021.3104165)**Yukiya Hono, Kei Hashimoto, Keiichiro Oura et al.*36 citations*
62. **[Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation ↗](https://doi.org/10.1109/taslp.2021.3129363)**Zhong-Qiu Wang, Gordon Wichern, Jonathan Le Roux*35 citations*
63. **[Multi-Channel Multi-Frame ADL-MVDR for Target Speech Separation ↗](https://doi.org/10.1109/taslp.2021.3129335)**Zhuohuang Zhang, Yong Xu, Meng Yu et al.*35 citations*
64. **[Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations ↗](https://doi.org/10.1109/taslp.2021.3138670)**Qian Li, Hao Ming Peng, Jianxin Li et al.*35 citations*
65. **[Voice Activity Detection in the Wild: A Data-Driven Approach Using Teacher-Student Training ↗](https://doi.org/10.1109/taslp.2021.3073596)**Heinrich Dinkel, Shuai Wang, Xuenan Xu et al.*35 citations*
66. **[Efficient Combinatorial Optimization for Word-Level Adversarial Textual Attack ↗](https://doi.org/10.1109/taslp.2021.3130970)**Shengcai Liu, Ning Lü, Cheng Chen et al.*34 citations*
67. **[Optimal Output-Constrained Active Noise Control Based on Inverse Adaptive Modeling Leak Factor Estimate ↗](https://doi.org/10.1109/taslp.2021.3065730)**Dongyuan Shi, Woon‐Seng Gan, Bhan Lam et al.*34 citations*
68. **[Target Speaker Verification With Selective Auditory Attention for Single and Multi-Talker Speech ↗](https://doi.org/10.1109/taslp.2021.3100682)**Chenglin Xu, Wei Rao, Jibin Wu et al.*34 citations*
69. **[Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning ↗](https://doi.org/10.1109/taslp.2021.3133189)**Haibin Wu, Li Xu, Andy T. Liu et al.*33 citations*
70. **[S-Vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder ↗](https://doi.org/10.1109/taslp.2021.3134566)**N J Metilda Sagaya Mary, Srinivasan Umesh, Sandesh V. Katta*33 citations*
71. **[Generation of Personal Sound Zones With Physical Meaningful Constraints and Conjugate Gradient Method ↗](https://doi.org/10.1109/taslp.2021.3052564)**Liming Shi, Taewoong Lee, Lijun Zhang et al.*32 citations*
72. **[A Wave Digital Newton-Raphson Method for Virtual Analog Modeling of Audio Circuits with Multiple One-Port Nonlinearities ↗](https://doi.org/10.1109/taslp.2021.3084337)**Alberto Bernardini, Enrico Bozzo, Federico Fontana et al.*31 citations*
73. **[Knowing Where to Leverage: Context-Aware Graph Convolutional Network With an Adaptive Fusion Layer for Contextual Spoken Language Understanding ↗](https://doi.org/10.1109/taslp.2021.3053400)**Libo Qin, Wanxiang Che, Minheng Ni et al.*31 citations*
74. **[A Novel Loss Function and Training Strategy for Noise-Robust Keyword Spotting ↗](https://doi.org/10.1109/taslp.2021.3092567)**Iván López‐Espejo, Zheng‐Hua Tan, Jesper Jensen*30 citations*
75. **[Beamforming with Cube Microphone Arrays Via Kronecker Product Decompositions ↗](https://doi.org/10.1109/taslp.2021.3079816)**Xuehan Wang, Jacob Benesty, Jingdong Chen et al.*30 citations*
76. **[Improving Skip-Gram Embeddings Using BERT ↗](https://doi.org/10.1109/taslp.2021.3065201)**Yile Wang, Leyang Cui, Yue Zhang*30 citations*
77. **[Learning Deep Direct-Path Relative Transfer Function for Binaural Sound Source Localization ↗](https://doi.org/10.1109/taslp.2021.3120641)**Bing Yang, Hong Liu, Xiaofei Li*30 citations*
78. **[Adaptive Adapters: An Efficient Way to Incorporate BERT Into Neural Machine Translation ↗](https://doi.org/10.1109/taslp.2021.3076863)**Junliang Guo, Zhirui Zhang, Linli Xu et al.*29 citations*
79. **[Learning Fine-Grained Fact-Article Correspondence in Legal Cases ↗](https://doi.org/10.1109/taslp.2021.3130992)**Jidong Ge, Yunyun huang, Xiaoyu Shen et al.*29 citations*
80. **[Conditioned Source Separation for Musical Instrument Performances ↗](https://doi.org/10.1109/taslp.2021.3082331)**Olga Slizovskaia, Gloria Haro, Emilia Gomez*28 citations*
81. **[Multi-Source Domain Adaptation for Text-Independent Forensic Speaker Recognition ↗](https://doi.org/10.1109/taslp.2021.3130975)**Zhenyu Wang, John H. L. Hansen*28 citations*
82. **[Converting Foreign Accent Speech Without a Reference ↗](https://doi.org/10.1109/taslp.2021.3060813)**Guanlong Zhao, Shaojin Ding, Ricardo Gutiérrez‐Osuna*27 citations*
83. **[Double-Cross-Correlation Processing for Blind Sampling-Rate and Time-Offset Estimation ↗](https://doi.org/10.1109/taslp.2021.3071967)**Aleksej Chinaev, Philipp Thüne, Gerald Enzner*27 citations*
84. **[Enhancing Segment-Based Speech Emotion Recognition by Iterative Self-Learning ↗](https://doi.org/10.1109/taslp.2021.3133195)**Shuiyang Mao, P.C. Ching, Tan Lee*27 citations*
85. **[Group Communication With Context Codec for Lightweight Source Separation ↗](https://doi.org/10.1109/taslp.2021.3078640)**Yi Luo, Cong Han, Nima Mesgarani*27 citations*
86. **[Neural Machine Translation With Explicit Phrase Alignment ↗](https://doi.org/10.1109/taslp.2021.3057831)**Jiacheng Zhang, Huanbo Luan, Maosong Sun et al.*27 citations*
87. **[On the Design of Differential Kronecker Product Beamformers ↗](https://doi.org/10.1109/taslp.2021.3069089)**Gal Itzhak, Jacob Benesty, Israel Cohen*27 citations*
88. **[PhaseDCN: A Phase-Enhanced Dual-Path Dilated Convolutional Network for Single-Channel Speech Enhancement ↗](https://doi.org/10.1109/taslp.2021.3092585)**Lu Zhang, Mingjiang Wang, Qiquan Zhang et al.*27 citations*
89. **[Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network ↗](https://doi.org/10.1109/taslp.2021.3061245)**Yi-Chiao Wu, Tomoki Hayashi, Patrick Lumban Tobing et al.*27 citations*
90. **[Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models ↗](https://doi.org/10.1109/taslp.2021.3133216)**Javier Jorge, Adrià Giménez, Joan Albert Silvestre-Cerdà et al.*26 citations*
91. **[Meta-Learning With Latent Space Clustering in Generative Adversarial Network for Speaker Diarization ↗](https://doi.org/10.1109/taslp.2021.3061885)**Monisankha Pal, Manoj Kumar, Raghuveer Peri et al.*26 citations*
92. **[Scalable and Efficient Neural Speech Coding: A Hybrid Design ↗](https://doi.org/10.1109/taslp.2021.3129353)**Kai Zhen, Jongmo Sung, Mi Suk Lee et al.*26 citations*
93. **[Word-Region Alignment-Guided Multimodal Neural Machine Translation ↗](https://doi.org/10.1109/taslp.2021.3138719)**Yuting Zhao, Mamoru Komachi, Tomoyuki Kajiwara et al.*26 citations*
94. **[Audio-Visual Multi-Channel Integration and Recognition of Overlapped Speech ↗](https://doi.org/10.1109/taslp.2021.3078883)**Jianwei Yu, Shi-Xiong Zhang, Bo Wu et al.*25 citations*
95. **[Deep Selective Memory Network With Selective Attention and Inter-Aspect Modeling for Aspect Level Sentiment Classification ↗](https://doi.org/10.1109/taslp.2021.3058540)**Peiqin Lin, Meng Yang, Jianhuang Lai*25 citations*
96. **[Diverse Distractor Generation for Constructing High-Quality Multiple Choice Questions ↗](https://doi.org/10.1109/taslp.2021.3138706)**Jiayuan Xie, Ningxin Peng, Yi Cai et al.*25 citations*
97. **[Domain-Aware Dialogue State Tracker for Multi-Domain Dialogue Systems ↗](https://doi.org/10.1109/taslp.2021.3054309)**Vevake Balaraman, Bernardo Magnini*25 citations*
98. **[Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction ↗](https://doi.org/10.1109/taslp.2021.3079812)**Zhiwen Xie, Runjie Zhu, Jin Liu et al.*25 citations*
99. **[On the Design of 3D Steerable Beamformers With Uniform Concentric Circular Microphone Arrays ↗](https://doi.org/10.1109/taslp.2021.3103129)**Xudong Zhao, Gongping Huang, Jingdong Chen et al.*25 citations*
100. **[TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition ↗](https://doi.org/10.1109/taslp.2021.3071662)**Ji Won Yoon, Hyeonseung Lee, Hyung Yong Kim et al.*25 citations*

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/2/) [3](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/3/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/papers/page/2/)

- [← back to](https://md.research.elamur.ai/free/en/venues/ieee-acm-transactions-on-audio-speech-and-language-processing/2021/) — IEEE/ACM Transactions on Audio Speech and Language Processing 2021