---
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 3 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/page/3/"
---
[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/page/3/)

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

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

281 papers · page 3 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/)

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

201. **[Medical Term and Status Generation From Chinese Clinical Dialogue With Multi-Granularity Transformer ↗](https://doi.org/10.1109/taslp.2021.3122301)**Mei Li, Lu Xiang, Xiaomian Kang et al.*10 citations*
202. **[Non-Linear-Echo Based Anti-Collusion Mechanism for Audio Signals ↗](https://doi.org/10.1109/taslp.2021.3058892)**Tianrui Zong, Yong Xiang, Iynkaran Natgunanathan et al.*10 citations*
203. **[Sparse Representations With Legendre Kernels for DOA Estimation and Acoustic Source Separation ↗](https://doi.org/10.1109/taslp.2021.3091845)**Mert Burkay Çöteli, Hüseyin Hachabiboğlu*10 citations*
204. **[Attending From Foresight: A Novel Attention Mechanism for Neural Machine Translation ↗](https://doi.org/10.1109/taslp.2021.3097939)**Xintong Li, Lemao Liu, Zhaopeng Tu et al.*9 citations*
205. **[Exploiting Translation Model for Parallel Corpus Mining ↗](https://doi.org/10.1109/taslp.2021.3105798)**Chongman Leong, Xuebo Liu, Derek F. Wong et al.*9 citations*
206. **[FifthNet: Structured Compact Neural Networks for Automatic Chord Recognition ↗](https://doi.org/10.1109/taslp.2021.3070158)**Ken O’Hanlon, Mark B. Sandler*9 citations*
207. **[Impulsive Noise Detection for Speech Enhancement in HHT Domain ↗](https://doi.org/10.1109/taslp.2021.3093392)**C.A. Medina, R. Coelho, Leonardo Zão*9 citations*
208. **[Iterative Echo Labeling Algorithm With Convex Hull Expansion for Room Geometry Estimation ↗](https://doi.org/10.1109/taslp.2021.3069093)**Sooyeon Park, Jung‐Woo Choi*9 citations*
209. **[Late-Reverberation Synthesis Using Interleaved Velvet-Noise Sequences ↗](https://doi.org/10.1109/taslp.2021.3060165)**Vesa Välimäki, Karolina Prawda*9 citations*
210. **[Multimodal Representations for Synchronized Speech and Real-Time MRI Video Processing ↗](https://doi.org/10.1109/taslp.2021.3084099)**Öykü Deniz Köse, Murat Saraçlar*9 citations*
211. **[Recurrent Neural Networks and Acoustic Features for Frame-Level Signal-to-Noise Ratio Estimation ↗](https://doi.org/10.1109/taslp.2021.3107617)**Hao Li, DeLiang Wang, Xueliang Zhang et al.*9 citations*
212. **[TAU-Net: Temporal Activation U-Net Shared With Nonnegative Matrix Factorization for Speech Enhancement in Unseen Noise Environments ↗](https://doi.org/10.1109/taslp.2021.3067154)**Kwang Myung Jeon, Geon Woo Lee, Nam Kyun Kim et al.*9 citations*
213. **[A Multi-Agent Communication Based Model for Nested Named Entity Recognition ↗](https://doi.org/10.1109/taslp.2021.3086978)**Canguang Li, Guohua Wang, Jin Cao et al.*8 citations*
214. **[Bayesian Estimation of PLDA in the Presence of Noisy Training Labels, With Applications to Speaker Verification ↗](https://doi.org/10.1109/taslp.2021.3130980)**Bengt J. Borgstrom*8 citations*
215. **[Binaural Auralization of Microphone Array Room Impulse Responses Using Causal Wiener Filtering ↗](https://doi.org/10.1109/taslp.2021.3110340)**Viktor Gunnarsson, Mikael Sternad*8 citations*
216. **[Deep Contextualized Utterance Representations for Response Selection and Dialogue Analysis ↗](https://doi.org/10.1109/taslp.2021.3074788)**Jia-Chen Gu, Tianda Li, Zhen-Hua Ling et al.*8 citations*
217. **[Domain Adaptive Meta-Learning for Dialogue State Tracking ↗](https://doi.org/10.1109/taslp.2021.3080182)**Jiali Zeng, Yongjing Yin, Yang Liu et al.*8 citations*
218. **[Learning Phone Recognition From Unpaired Audio and Phone Sequences Based on Generative Adversarial Network ↗](https://doi.org/10.1109/taslp.2021.3138720)**Da-Rong Liu, Po-chun Hsu, Yi‐Chen Chen et al.*8 citations*
219. **[Learning Waveform-Based Acoustic Models Using Deep Variational Convolutional Neural Networks ↗](https://doi.org/10.1109/taslp.2021.3104193)**Dino Oglic, Zoran Cvetkovic, Peter Sollich A*8 citations*
220. **[Near-Field Superdirectivity: An Analytical Perspective ↗](https://doi.org/10.1109/taslp.2021.3070686)**Dovid Y. Levin, Shmulik Markovich‐Golan, Sharon Gannot*8 citations*
221. **[Synthesizing Spoken Descriptions of Images ↗](https://doi.org/10.1109/taslp.2021.3120644)**Xinsheng Wang, Justin van der Hout, Jihua Zhu et al.*8 citations*
222. **[Temporal Dynamics of Workplace Acoustic Scenes: Egocentric Analysis and Prediction ↗](https://doi.org/10.1109/taslp.2021.3050265)**Arindam Jati, Amrutha Nadarajan, Raghuveer Peri et al.*8 citations*
223. **[The Effect of Partial Time-Frequency Masking of the Direct Sound on the Perception of Reverberant Speech ↗](https://doi.org/10.1109/taslp.2021.3084742)**Lior Madmoni, Shir Tibor, Israel Nelken et al.*8 citations*
224. **[A Causality-Constrained Frequency-Domain Least-Squares Filter Design Method for Crosstalk Cancellation ↗](https://doi.org/10.1109/taslp.2021.3110651)**Tobias Kabzinski, Peter Jax*7 citations*
225. **[Gated Recurrent Context: Softmax-Free Attention for Online Encoder-Decoder Speech Recognition ↗](https://doi.org/10.1109/taslp.2021.3049344)**Hyeonseung Lee, Woo Hyun Kang, Sung Jun Cheon et al.*7 citations*
226. **[HDRS: Hindi Dialogue Restaurant Search Corpus for Dialogue State Tracking in Task-Oriented Environment ↗](https://doi.org/10.1109/taslp.2021.3065833)**Shrikant Malviya, Rohit Mishra, Santosh Kumar Barnwal et al.*7 citations*
227. **[Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data ↗](https://doi.org/10.1109/taslp.2021.3066274)**Ye Bai, Jiangyan Yi, Jianhua Tao et al.*7 citations*
228. **[Learning Context-Aware Convolutional Filters for Implicit Discourse Relation Classification ↗](https://doi.org/10.1109/taslp.2021.3096041)**Kashif Munir, Hai Zhao, Zuchao Li*7 citations*
229. **[Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking of Fundamental Frequency ↗](https://doi.org/10.1109/taslp.2021.3067161)**Aidan O. T. Hogg, Christine Evers, Alastair H. Moore et al.*7 citations*
230. **[Second-Order Semantic Role Labeling With Global Structural Refinement ↗](https://doi.org/10.1109/taslp.2021.3082706)**Hao Fei, Shengqiong Wu, Yafeng Ren et al.*7 citations*
231. **[Sound Field Reproduction With a Cylindrical Loudspeaker Array Using First Order Wall Reflections ↗](https://doi.org/10.1109/taslp.2021.3120590)**Natsuko Maeda, Filippo Maria Fazi, Falk-Martin Hoffmann*7 citations*
232. **[Synthesis and Analysis-By-Synthesis of Modulated Diplophonic Glottal Area Waveforms ↗](https://doi.org/10.1109/taslp.2021.3053387)**Philipp Aichinger, Franz Pernkopf*7 citations*
233. **[Text Generation From Data With Dynamic Planning ↗](https://doi.org/10.1109/taslp.2021.3129346)**Sen Yang, Yang Liu, Dawei Feng et al.*7 citations*
234. **[Ambisonic Signal Processing DNNs Guaranteeing Rotation, Scale and Time Translation Equivariance ↗](https://doi.org/10.1109/taslp.2021.3069193)**Ryotaro Sato, Kenta Niwa, Kazunori Kobayashi*6 citations*
235. **[Coupling a Generative Model With a Discriminative Learning Framework for Speaker Verification ↗](https://doi.org/10.1109/taslp.2021.3129360)**Xugang Lu, Peng Shen, Yu Tsao et al.*6 citations*
236. **[Estimation of Spectral Notches From Pinna Meshes: Insights From a Simple Computational Model ↗](https://doi.org/10.1109/taslp.2021.3101928)**Simone Spagnol, Riccardo Miccini, Marius George Onofrei et al.*6 citations*
237. **[Exploring Multi-Stage Information Interactions for Multi-Source Neural Machine Translation ↗](https://doi.org/10.1109/taslp.2021.3120592)**Ziyao Lu, Xianglin Li, Yang Liu et al.*6 citations*
238. **[GRTr: Generative-Retrieval Transformers for Data-Efficient Dialogue Domain Adaptation ↗](https://doi.org/10.1109/taslp.2021.3074779)**Igor Shalyminov, Alessandro Sordoni, Adam Atkinson et al.*6 citations*
239. **[Gamma Boltzmann Machine for Audio Modeling ↗](https://doi.org/10.1109/taslp.2021.3095656)**Toru Nakashika, Kohei Yatabe*6 citations*
240. **[Incorporating Wireless Communication Parameters Into the E-Model Algorithm ↗](https://doi.org/10.1109/taslp.2021.3057955)**Demóstenes Zegarra Rodríguez, Dick Carrillo, Miguel Arjona Ramírez et al.*6 citations*
241. **[Robustness of Acoustic Rake Filters in Minimum Variance Beamforming ↗](https://doi.org/10.1109/taslp.2021.3126946)**Ran Weisman, Tom Shlomo, Vladimir Tourbabin et al.*6 citations*
242. **[SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points ↗](https://doi.org/10.1109/taslp.2021.3133209)**Yu-Chen Lin, Cheng Yu, Yi-Te Hsu et al.*6 citations*
243. **[Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data ↗](https://doi.org/10.1109/taslp.2021.3066047)**Mingyang Zhang, Yi Zhou, Zhao Li et al.*6 citations*
244. **[A Multiple-Integration Encoder for Multi-Turn Text-to-SQL Semantic Parsing ↗](https://doi.org/10.1109/taslp.2021.3070726)**Run-Ze Wang, Zhen-Hua Ling, Jingbo Zhou et al.*5 citations*
245. **[Audio-Aware Spoken Multiple-Choice Question Answering With Pre-Trained Language Models ↗](https://doi.org/10.1109/taslp.2021.3120638)**Chia-Chih Kuo, Kuan-Yu Chen, Shang-Bao Luo*5 citations*
246. **[Corruption Is Not All Bad: Incorporating Discourse Structure Into Pre-Training via Corruption for Essay Scoring ↗](https://doi.org/10.1109/taslp.2021.3088223)**Farjana Sultana Mim, Naoya Inoue, Paul Reisert et al.*5 citations*
247. **[DNN-Based Mask Estimation for Distributed Speech Enhancement in Spatially Unconstrained Microphone Arrays ↗](https://doi.org/10.1109/taslp.2021.3092838)**Nicolas Furnon, Romain Serizel, Slim Essid et al.*5 citations*
248. **[Detecting Source Contextual Barriers for Understanding Neural Machine Translation ↗](https://doi.org/10.1109/taslp.2021.3085119)**Guanlin Li, Lemao Liu, Conghui Zhu et al.*5 citations*
249. **[Localization Based on Enhanced Low Frequency Interaural Level Difference ↗](https://doi.org/10.1109/taslp.2021.3111583)**Metin Calis, Steven van de Par, Richard R. Heusdens et al.*5 citations*
250. **[Multichannel Iterative Noise Reduction Filters in the Short-Time-Fourier-Transform Domain Based on Kronecker Product Decomposition ↗](https://doi.org/10.1109/taslp.2021.3092825)**Xianghui Wang, Jie Chen, Xiaoyi Chen et al.*5 citations*
251. **[Native-Nonnative Voice Conversion by Residual Warping in a Sparse, Anchor-Based Representation ↗](https://doi.org/10.1109/taslp.2021.3111568)**Christopher Liberatore*5 citations*
252. **[Partially Matching Projection Decoding Method Evaluation Under Different Playback Conditions ↗](https://doi.org/10.1109/taslp.2021.3068002)**Zhongshu Ge, Liang Li, Tianshu Qu*5 citations*
253. **[UnitNet: A Sequence-to-Sequence Acoustic Model for Concatenative Speech Synthesis ↗](https://doi.org/10.1109/taslp.2021.3093823)**Zhou Xiao, Zhen-Hua Ling, Li-Rong Dai*5 citations*
254. **[Vocal Tract Length Estimation Using Accumulated Means of Formants and Its Effects on Speaker-Normalization ↗](https://doi.org/10.1109/taslp.2021.3060172)**Tadashi Sakata, Naomitsu Ikeda, Yuichi Ueda et al.*5 citations*
255. **[Efficient Learning Approach for Pronominal Anaphora and Ellipsis Identification and Resolution in Arabic Texts ↗](https://doi.org/10.1109/taslp.2021.3120649)**Saoussen Mathlouthi Bouzid, Chiraz Ben Othmane Zribi*4 citations*
256. **[End-to-End Recurrent Cross-Modality Attention for Video Dialogue ↗](https://doi.org/10.1109/taslp.2021.3065852)**Yun-Wei Chu, Kuan-Yen Lin, Chao-Chun Hsu et al.*4 citations*
257. **[Label and Context Augmentation for Response Selection at DSTC8 ↗](https://doi.org/10.1109/taslp.2021.3076876)**Myeongho Jeong, Seungtaek L. Choi, Jinyoung Yeo et al.*4 citations*
258. **[Minimum Processing Beamforming ↗](https://doi.org/10.1109/taslp.2021.3053411)**Adel Zahedi, Michael Syskind Pedersen, Jan Stubbe Østergaard et al.*4 citations*
259. **[Sentiment Time Series Calibration for Event Detection ↗](https://doi.org/10.1109/taslp.2021.3096653)**Jingyi Wu, Lin Shang, Xiaoying Gao*4 citations*
260. **[Subword-Based Compact Reconstruction for Open-Vocabulary Neural Word Embeddings ↗](https://doi.org/10.1109/taslp.2021.3125133)**Shota Sasaki, Jun Suzuki, Kentaro Inui*4 citations*
261. **[Syntax-Aware Multi-Spans Generation for Reading Comprehension ↗](https://doi.org/10.1109/taslp.2021.3138679)**Zhuosheng Zhang, Yiqing Zhang, Hai Zhao*4 citations*
262. **[Corpus-Aware Graph Aggregation Network for Sequence Labeling ↗](https://doi.org/10.1109/taslp.2021.3084105)**Haibin Chen, Qianli Ma, Liuhong Yu et al.*3 citations*
263. **[Learning Cross-Lingual Mappings in Imperfectly Isomorphic Embedding Spaces ↗](https://doi.org/10.1109/taslp.2021.3097935)**Yuling Li, Kui Yu, Yuhong Zhang*3 citations*
264. **[Multi-Granularity Sequence Alignment Mapping for Encoder-Decoder Based End-to-End ASR ↗](https://doi.org/10.1109/taslp.2021.3101921)**Jian Tang, Jie Zhang, Yan Song et al.*3 citations*
265. **[Predict-Then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems ↗](https://doi.org/10.1109/taslp.2021.3110145)**Zehao Lin, Shaobo Cui, Guodun Li et al.*3 citations*
266. **[The Harmonic Shift Algorithm for Efficient Multi-Pitch Detection ↗](https://doi.org/10.1109/taslp.2021.3129344)**Lukas Grinewitschus, Peter Jung*3 citations*
267. **[2021 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 29 ↗](https://doi.org/10.1109/taslp.2022.3147096)***2 citations*
268. **[Asynchronous Decentralized Distributed Training of Acoustic Models ↗](https://doi.org/10.1109/taslp.2021.3122349)**Xiaodong Cui, Wei Zhang, Abdullah Kayi et al.*2 citations*
269. **[Effects of Additive Noise in Binaural Rendering of Spherical Microphone Array Signals ↗](https://doi.org/10.1109/taslp.2021.3129359)**Hannes Helmholz, David Lou Alon, Sebastià V. Amengual Garí et al.*2 citations*
270. **[Efficient Estimate of Sentence's Representation Based on the Difference Semantics Model ↗](https://doi.org/10.1109/taslp.2021.3123885)**Xianwen Liao, Yongzhong Huang, Yongzhuang Wei et al.*2 citations*
271. **[F0 Perturbation Due to Articulatory Movements: Filtering, Characterization and Applications ↗](https://doi.org/10.1109/taslp.2021.3082671)**Humberto Torres, María Mercedes Güemes, Jorge A. Gurlekian et al.*2 citations*
272. **[Generating Responses With a Given Syntactic Pattern in Chinese Dialogues ↗](https://doi.org/10.1109/taslp.2021.3110124)**Yi Xuan Zhou, Xiaoqing Zheng, Xuanjing Huang*2 citations*
273. **[Improved Acoustic Word Embeddings for Zero-Resource Languages Using Multilingual Transfer ↗](https://doi.org/10.1109/taslp.2021.3060805)**Herman Kamper, Yevgen Matusevych, Sharon J. Goldwater*2 citations*
274. **[VACE-WPE: Virtual Acoustic Channel Expansion Based on Neural Networks for Weighted Prediction Error-Based Speech Dereverberation ↗](https://doi.org/10.1109/taslp.2021.3133190)**Joon‐Young Yang, Joon‐Hyuk Chang*2 citations*
275. **[Weighted Orthogonal Vector Rejection Method for Loudspeaker-Based Binaural Audio Reproduction ↗](https://doi.org/10.1109/taslp.2021.3080915)**Eric Hamdan, Filippo Maria Fazi*2 citations*
276. **[Articulatory Synthesis of Vocalized /r/ Allophones in German ↗](https://doi.org/10.1109/taslp.2021.3130969)**Simon Stone, Yingming Gao, Peter Birkholz*1 citation*
277. **[HPSG-Inspired Joint Neural Constituent and Dependency Parsing in O(n³) Time Complexity ↗](https://doi.org/10.1109/taslp.2021.3138715)**Zuchao Li, Junru Zhou, Hai Zhao et al.*1 citation*
278. **[Uncertainty-Aware Sequence Labeling ↗](https://doi.org/10.1109/taslp.2021.3138680)**Jiacheng Ye, Xiang Zhou, Xiaoqing Zheng et al.*1 citation*
279. **[Unsupervised Character Embedding Correction and Candidate Word Denoising ↗](https://doi.org/10.1109/taslp.2021.3129334)**Kengtao Zheng, Nankai Lin, Jiang Shengyi*1 citation*
280. **[Which Apple Keeps Which Doctor Away? Colorful Word Representations With Visual Oracles ↗](https://doi.org/10.1109/taslp.2021.3130972)**Zhuosheng Zhang, Haojie Yu, Hai Zhao et al.*1 citation*
281. **[Editorial: Special Issue on the Eighth Dialog System Technology Challenge ↗](https://doi.org/10.1109/taslp.2021.3097842)**Seokhwan Kim, Hannes Schulz, Chulaka Gunasekara et al.

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

- [← 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