---
title: "Computer Speech & Language 2021 — all accepted papers"
description: "All 95 papers of Computer Speech & Language 2021, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/computer-speech-language/2021/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/computer-speech-language/2021/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Computer Speech & Language](https://md.research.elamur.ai/free/en/venues/computer-speech-language/) / [2021](https://md.research.elamur.ai/free/en/venues/computer-speech-language/2021/) / papers

# Computer Speech & Language 2021: all accepted papers

95 papers · the most cited first · [← Computer Speech & Language 2021](https://md.research.elamur.ai/free/en/venues/computer-speech-language/2021/)

1. **[A review of speaker diarization: Recent advances with deep learning ↗](https://doi.org/10.1016/j.csl.2021.101317)**Tae‐Jin Park, Naoyuki Kanda, Dimitrios Dimitriadis et al.*354 citations*
2. **[Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: Theory, implementation and analysis on standard tasks ↗](https://doi.org/10.1016/j.csl.2021.101254)**Federico Landini, Ján Profant, Mireia Díez et al.*175 citations*
3. **[Attention-based BiLSTM fused CNN with gating mechanism model for Chinese long text classification ↗](https://doi.org/10.1016/j.csl.2020.101182)**Jianfeng Deng, Lianglun Cheng, Zhuowei Wang*157 citations*
4. **[Deep reinforcement and transfer learning for abstractive text summarization: A review ↗](https://doi.org/10.1016/j.csl.2021.101276)**Ayham Alomari, Norisma Binti Idris, Aznul Qalid Md Sabri et al.*137 citations*
5. **[Spoken language interaction with robots: Recommendations for future research ↗](https://doi.org/10.1016/j.csl.2021.101255)**Matthew Marge, Carol Espy-Wilson, Nigel Ward et al.*107 citations*
6. **[Combining context-relevant features with multi-stage attention network for short text classification ↗](https://doi.org/10.1016/j.csl.2021.101268)**Yingying Liu, Peipei Li, Xuegang Hu*83 citations*
7. **[Enhancing Arabic aspect-based sentiment analysis using deep learning models ↗](https://doi.org/10.1016/j.csl.2021.101224)**Saja Al-Dabet, Sara Tedmori, Mohammad AL-Smadi*77 citations*
8. **[Generative adversarial networks for speech processing: A review ↗](https://doi.org/10.1016/j.csl.2021.101308)**Aamir Wali, Zareen Alamgir, Saira Karim et al.*77 citations*
9. **[Non-negative matrix factorization-based time-frequency feature extraction of voice signal for Parkinson's disease prediction ↗](https://doi.org/10.1016/j.csl.2021.101216)**Biswajit Karan, Sitanshu Sekhar Sahu, Juan Rafael Orozco‐Arroyave et al.*73 citations*
10. **[An automatic Alzheimer’s disease classifier based on spontaneous spoken English ↗](https://doi.org/10.1016/j.csl.2021.101298)**Flavio Bertini, Davide Allevi, Gianluca Lutero et al.*66 citations*
11. **[Adversarial attack and defense strategies for deep speaker recognition systems ↗](https://doi.org/10.1016/j.csl.2021.101199)**Arindam Jati, Chin-Cheng Hsu, Monisankha Pal et al.*63 citations*
12. **[Arabic speech recognition by end-to-end, modular systems and human](https://md.research.elamur.ai/free/en/papers/hussein-2021-arabic-speech-recognition-end-end/)**Amir Hussein, Shinji Watanabe, Ahmed M. Abdelatty Ali*62 citations · our summary*
13. **[BERT syntactic transfer: A computational experiment on Italian, French and English languages ↗](https://doi.org/10.1016/j.csl.2021.101261)**Raffaele Guarasci, Stefano Silvestri, Giuseppe De Pietro et al.*55 citations*
14. **[Analysis and classification of speech sounds of children with autism spectrum disorder using acoustic features ↗](https://doi.org/10.1016/j.csl.2021.101287)**Abhijit Mohanta, Vinay Kumar Mittal*54 citations*
15. **[The automatic detection of heart failure using speech signals ↗](https://doi.org/10.1016/j.csl.2021.101205)**Mittapalle Kiran Reddy, Pyry Helkkula, Y. Madhu Keerthana et al.*47 citations*
16. **[Investigations on speech recognition systems for low-resource dialectal Arabic–English code-switching speech ↗](https://doi.org/10.1016/j.csl.2021.101278)**Injy Hamed, Pavel Denisov, Chia-Yu Li et al.*45 citations*
17. **[Comprehensive analysis of aspect term extraction methods using various text embeddings ↗](https://doi.org/10.1016/j.csl.2021.101217)**Łukasz Augustyniak, Tomasz Jan Kajdanowicz, Przemysław Kazienko*44 citations*
18. **[Evaluating voice-assistant commands for dementia detection ↗](https://doi.org/10.1016/j.csl.2021.101297)**Xiaohui Liang, John A. Batsis, Youxiang Zhu et al.*43 citations*
19. **[Prediction of speech intelligibility with DNN-based performance measures ↗](https://doi.org/10.1016/j.csl.2021.101329)**Angel Mario Castro Martínez, Constantin Spille, Jana Roßbach et al.*40 citations*
20. **[End-to-end neural systems for automatic children speech recognition: An empirical study ↗](https://doi.org/10.1016/j.csl.2021.101289)**Prashanth Gurunath Shivakumar, Shrikanth Shri Narayanan*39 citations*
21. **[Verbal fluency in normal aging and cognitive decline: Results of a longitudinal study ↗](https://doi.org/10.1016/j.csl.2021.101195)**Claudia Frankenberg, Jochen Weiner, Maren Knebel et al.*38 citations*
22. **[Discriminating speech traits of Alzheimer's disease assessed through a corpus of reading task for Spanish language ↗](https://doi.org/10.1016/j.csl.2021.101341)**Olga Ivanova, Juan José García Meilán, Francisco Martínez‐Sánchez et al.*34 citations*
23. **[Deep ad-hoc beamforming ↗](https://doi.org/10.1016/j.csl.2021.101201)**Xiao-Lei Zhang*29 citations*
24. **[Language-independent extractive automatic text summarization based on automatic keyword extraction ↗](https://doi.org/10.1016/j.csl.2021.101267)**Ángel Hernández-Castañeda, René Arnulfo García-Hernández, Yulia Nikolaevna Ledeneva et al.*29 citations*
25. **[Siamese networks for large-scale author identification ↗](https://doi.org/10.1016/j.csl.2021.101241)**Chakaveh Saedi, Mark Dras*27 citations*
26. **[Accentron: Foreign accent conversion to arbitrary non-native speakers using zero-shot learning ↗](https://doi.org/10.1016/j.csl.2021.101302)**Shaojin Ding, Guanlong Zhao, Ricardo Gutiérrez‐Osuna*26 citations*
27. **[Phase sensitive masking-based single channel speech enhancement using conditional generative adversarial network ↗](https://doi.org/10.1016/j.csl.2021.101270)**Sidheswar Routray, Qirong Mao*26 citations*
28. **[A multi-label emoji classification method using balanced pointwise mutual information-based feature selection ↗](https://doi.org/10.1016/j.csl.2021.101330)**Zahra Ahanin, Maizatul Akmar Ismail*24 citations*
29. **[Dialect Identification using Chroma-Spectral Shape Features with Ensemble Technique ↗](https://doi.org/10.1016/j.csl.2021.101230)**Nagaratna B. Chittaragi, Shashidhar G. Koolagudi*24 citations*
30. **[NUVA: A Naming Utterance Verifier for Aphasia Treatment ↗](https://doi.org/10.1016/j.csl.2021.101221)**David S. Barbera, Mark A. Huckvale, Victoria Fleming et al.*24 citations*
31. **[Natural language processing for under-resourced languages: Developing a Welsh natural language toolkit ↗](https://doi.org/10.1016/j.csl.2021.101311)**Daniel Cunliffe, Andreas Vlachidis, Daniel Williams et al.*23 citations*
32. **[Overlapped Speech Detection and speaker counting using distant microphone arrays ↗](https://doi.org/10.1016/j.csl.2021.101306)**Samuele Cornell, Maurizio Omologo, Stefano Squartini et al.*22 citations*
33. **[Representation transfer learning from deep end-to-end speech recognition networks for the classification of health states from speech ↗](https://doi.org/10.1016/j.csl.2021.101204)**Benjamin Sertolli, Zhao Xu Ren, Björn Wolfgang Schuller et al.*22 citations*
34. **[Changes in facial expressions in patients with Parkinson's disease during the phonation test and their correlation with disease severity ↗](https://doi.org/10.1016/j.csl.2021.101286)**Liqiong Yang, Xiangling Chen, Quanhao Guo et al.*21 citations*
35. **[Improving low-resource machine transliteration by using 3-way transfer learning ↗](https://doi.org/10.1016/j.csl.2021.101283)**Chun-Kai Wu, Chao-Chuang Shih, Yu-Chun Wang et al.*21 citations*
36. **[Code-switched automatic speech recognition in five South African languages ↗](https://doi.org/10.1016/j.csl.2021.101262)**Astik Biswas, Emre Yılmaz, Ewald van der Westhuizen et al.*20 citations*
37. **[Towards a unified assessment framework of speech pseudonymisation ↗](https://doi.org/10.1016/j.csl.2021.101299)**‪Paul-Gauthier Noé‬, Andreas Nautsch, Nicholas Evans et al.*20 citations*
38. **[Improving the potential of Enhanced Teager Energy Cepstral Coefficients (ETECC) for replay attack detection ↗](https://doi.org/10.1016/j.csl.2021.101281)**Ankur T. Patil, Rajul Acharya, Hemant A. Patil et al.*19 citations*
39. **[Perceptions and reactions to conversational privacy initiated by a conversational user interface ↗](https://doi.org/10.1016/j.csl.2021.101269)**Birgit Brüggemeier, Philip Lalone*19 citations*
40. **[Speaker anonymization by modifying fundamental frequency and x-vector singular value ↗](https://doi.org/10.1016/j.csl.2021.101326)**Candy Olivia Mawalim, Kasorn Galajit, Jessada Karnjana et al.*19 citations*
41. **[A classification benchmark for Arabic alphabet phonemes with diacritics in deep neural networks ↗](https://doi.org/10.1016/j.csl.2021.101274)**Eiad Almekhlafi, Moeen AL-Makhlafi, Erlei Zhang et al.*18 citations*
42. **[Joint emotion label space modeling for affect lexica ↗](https://doi.org/10.1016/j.csl.2021.101257)**Luna De Bruyne, Pepa Atanasova, Isabelle Augenstein*18 citations*
43. **[A speaker verification backend with robust performance across conditions ↗](https://doi.org/10.1016/j.csl.2021.101258)**Luciana Ferrer, Mitchell McLaren, Niko Brümmer*17 citations*
44. **[Cross-lingual detection of mild cognitive impairment based on temporal parameters of spontaneous speech ↗](https://doi.org/10.1016/j.csl.2021.101215)**Gábor Gosztolya, Réka Balogh, Nóra Imre et al.*17 citations*
45. **[Feature learning for efficient ASR-free keyword spotting in low-resource languages ↗](https://doi.org/10.1016/j.csl.2021.101275)**Ewald van der Westhuizen, Herman Kamper, Raghav Menon et al.*17 citations*
46. **[Paralinguistic and linguistic fluency features for Alzheimer's disease detection ↗](https://doi.org/10.1016/j.csl.2021.101198)**Edward L. Campbell, Raúl Yañez Mesía, Laura Docío-Fernández et al.*17 citations*
47. **[Automatic speaker independent dysarthric speech intelligibility assessment system ↗](https://doi.org/10.1016/j.csl.2021.101213)**Ayush Tripathi, Swapnil Bhosale, Sunil Kumar Kopparapu*15 citations*
48. **[Conversation Initiation of Mothers, Fathers, and Toddlers in their Natural Home Environment ↗](https://doi.org/10.1016/j.csl.2021.101338)**Mark VanDam, Lauren Thompson, Elizabeth B. Wilson-Fowler et al.*15 citations*
49. **[Multi-level embeddings for processing Arabic social media contents ↗](https://doi.org/10.1016/j.csl.2021.101240)**Leila Moudjari, Farah Benamara, Karima Akli‐Astouati*14 citations*
50. **[The phonetic footprint of Parkinson’s disease ↗](https://doi.org/10.1016/j.csl.2021.101321)**Philipp Klumpp, Tomás Arias‐Vergara, Juan Camilo Vásquez-Correa et al.*13 citations*
51. **[A novel approach to unsupervised pattern discovery in speech using Convolutional Neural Network ↗](https://doi.org/10.1016/j.csl.2021.101259)**Kishore Kumar R, Kanishka Rao*12 citations*
52. **[Cross-lingual transfer learning for relation extraction using Universal Dependencies ↗](https://doi.org/10.1016/j.csl.2021.101265)**Nasrin Taghizadeh, Heshaam Faili*12 citations*
53. **[Empirical Mode Decomposition articulation feature extraction on Parkinson’s Diadochokinesia ↗](https://doi.org/10.1016/j.csl.2021.101322)**Alice Rueda, Juan Camilo Vásquez-Correa, Juan Rafael Orozco‐Arroyave et al.*11 citations*
54. **[MASS: Multi-task anthropomorphic speech synthesis framework ↗](https://doi.org/10.1016/j.csl.2021.101243)**Jinyin Chen, Linhui Ye, Zhaoyan Ming*11 citations*
55. **[Effectiveness of energy separation-based instantaneous frequency estimation for cochlear cepstral features for synthetic and voice-converted spoofed speech detection ↗](https://doi.org/10.1016/j.csl.2021.101301)**Ankur T. Patil, Hemant A. Patil, Kuldeep Khoria*10 citations*
56. **[Glottal features for classification of phonation type from speech and neck surface accelerometer signals ↗](https://doi.org/10.1016/j.csl.2021.101232)**Sudarsana Reddy Kadiri, Paavo Alku*10 citations*
57. **[Adjustable deterministic pseudonymization of speech ↗](https://doi.org/10.1016/j.csl.2021.101284)**S. Pavankumar Dubagunta, R.J.J.H. van Son, Mathew Magimai.-Doss*9 citations*
58. **[DORA: Towards policy optimization for task-oriented dialogue system with efficient context ↗](https://doi.org/10.1016/j.csl.2021.101310)**Hyunmin Jeon, Gary Geunbae Lee*9 citations*
59. **[Exploring accidental triggers of smart speakers ↗](https://doi.org/10.1016/j.csl.2021.101328)**Lea Schönherr, Maximilian Golla, Thorsten Eisenhofer et al.*9 citations*
60. **[Generating identities with mixture models for speaker anonymization ↗](https://doi.org/10.1016/j.csl.2021.101318)**Henry Turner, Giulio Lovisotto, Ivan Martinović*9 citations*
61. **[The predictive capabilities of mathematical models for the type-token relationship in English language corpora ↗](https://doi.org/10.1016/j.csl.2021.101227)**Martin J. Tunnicliffe, Gordon Hunter*8 citations*
62. **[Dereverberation of autoregressive envelopes for far-field speech recognition ↗](https://doi.org/10.1016/j.csl.2021.101277)**Anurenjan Purushothaman, Anirudh Sreeram, Rohit Vishal Kumar et al.*7 citations*
63. **[Sequential routing framework: Fully capsule network-based speech recognition ↗](https://doi.org/10.1016/j.csl.2021.101228)**Kyungmin Lee, Hyunwhan Joe, Hyeontaek Lim et al.*7 citations*
64. **[An intention multiple-representation model with expanded information ↗](https://doi.org/10.1016/j.csl.2021.101196)**Jingxiang Hu, Junjie Peng, Wenqiang Zhang et al.*6 citations*
65. **[Joint speaker diarization and speech recognition based on region proposal networks ↗](https://doi.org/10.1016/j.csl.2021.101316)**Zili Huang, Marc Delcroix, Leibny Paola Garcia et al.*6 citations*
66. **[Parameterisation of human speech after total laryngectomy surgery ↗](https://doi.org/10.1016/j.csl.2021.101313)**Krzysztof Tyburek*6 citations*
67. **[A combined syntactic-semantic embedding model based on lexicalized tree-adjoining grammar ↗](https://doi.org/10.1016/j.csl.2021.101202)**Hoang-Vu Dang, Phuong Le-Hong*5 citations*
68. **[Automated grapheme-to-phoneme conversion for Central Kurdish based on optimality theory ↗](https://doi.org/10.1016/j.csl.2021.101222)**Aso Mahmudi, Hadi Veisi*5 citations*
69. **[Cross-language article linking with deep neural network based paragraph encoding ↗](https://doi.org/10.1016/j.csl.2021.101279)**Yu-Chun Wang, Chia-Min Chuang, Chun-Kai Wu et al.*5 citations*
70. **[MS-Transformer: Introduce multiple structural priors into a unified transformer for encoding sentences ↗](https://doi.org/10.1016/j.csl.2021.101304)**Qi Le, Yu Zhang, Qingyu Yin et al.*5 citations*
71. **[Novel textual entailment technique for the Arabic language using genetic algorithm ↗](https://doi.org/10.1016/j.csl.2021.101194)**Bushra Alhijawi, Arafat Awajan*5 citations*
72. **[A study of vowel nasalization using instantaneous spectra ↗](https://doi.org/10.1016/j.csl.2021.101214)**RaviShankar Prasad, B. Yegnanarayana*4 citations*
73. **[Causal indicators for assessing the truthfulness of child speech in forensic interviews ↗](https://doi.org/10.1016/j.csl.2021.101263)**Zane Durante, Victor Ardulov, Manoj Kumar et al.*4 citations*
74. **[Comparison of rule-based and data-driven approaches for syllabification of simple syllable languages and the effect of orthography ↗](https://doi.org/10.1016/j.csl.2021.101233)**Franklin Ọládiípọ̀ Asahiah*4 citations*
75. **[Lightweight and irreversible speech pseudonymization based on data-driven optimization of cascaded voice modification modules ↗](https://doi.org/10.1016/j.csl.2021.101315)**Hiroto Kai, Shinnosuke Takamichi, Sayaka Shiota et al.*4 citations*
76. **[Prosodic event detection in children’s read speech ↗](https://doi.org/10.1016/j.csl.2021.101200)**Kamini Sabu, Preeti Rao*4 citations*
77. **[Stochastic models of glottal pulses from the Rosenberg and Liljencrants-Fant models with unified parameters ↗](https://doi.org/10.1016/j.csl.2021.101225)**Edson Cataldo, Diego S. M. Bahiano*4 citations*
78. **[Unsupervised speech representation learning for behavior modeling using triplet enhanced contextualized networks ↗](https://doi.org/10.1016/j.csl.2021.101226)**Haoqi Li, Brian Baucom, Shrikanth Shri Narayanan et al.*4 citations*
79. **[An investigation of neural uncertainty estimation for target speaker extraction equipped RNN transducer ↗](https://doi.org/10.1016/j.csl.2021.101327)**Jiatong Shi, Chunlei Zhang, Chao Weng et al.*3 citations*
80. **[Automatic detection of pharyngeal fricatives in cleft palate speech using acoustic features based on the vocal tract area spectrum ↗](https://doi.org/10.1016/j.csl.2021.101203)**Jia Fu, Fei He, Heng Yin et al.*3 citations*
81. **[Self-segmentation of pass-phrase utterances for deep feature learning in text-dependent speaker verification ↗](https://doi.org/10.1016/j.csl.2021.101229)**Achintya Kumar Sarkar, Zheng‐Hua Tan*3 citations*
82. **[Sentence transition matrix: An efficient approach that preserves sentence semantics ↗](https://doi.org/10.1016/j.csl.2021.101266)**Myeongjun Jang, Pilsung Kang*3 citations*
83. **[Symbolic and Statistical Learning Approaches to Speech Summarization: A Scoping Review ↗](https://doi.org/10.1016/j.csl.2021.101305)**Dana Rezazadegan, Shlomo Berkovsky, Juan C. Quiroz et al.*3 citations*
84. **[Adversarial subsequences for unconditional text generation ↗](https://doi.org/10.1016/j.csl.2021.101242)**Xingyuan Chen, Peng Jin, Yanzhe Li et al.*2 citations*
85. **[Exploring intrinsic information content models for addressing the issues of traditional semantic measures to evaluate verb similarity ↗](https://doi.org/10.1016/j.csl.2021.101280)**M. Krishna Siva Prasad, Poonam Sharma*2 citations*
86. **[Local and non-local dependency learning and emergence of rule-like representations in speech data by deep convolutional generative adversarial networks ↗](https://doi.org/10.1016/j.csl.2021.101244)**Gašper Beguš*2 citations*
87. **[Unsupervised sign language validation process based on hand-motion parameter clustering ↗](https://doi.org/10.1016/j.csl.2021.101256)**Mehrez Boulares, Ahmed Barnawi*2 citations*
88. **[Combining background noise and artificial masking to achieve privacy in sound zones ↗](https://doi.org/10.1016/j.csl.2021.101285)**Daniel Wallace, Jordan Cheer*1 citation*
89. **[Detection of vowel transition regions from Hindi language ↗](https://doi.org/10.1016/j.csl.2021.101231)**Jainath Yadav*1 citation*
90. **[GEPC: Global embeddings with PID control ↗](https://doi.org/10.1016/j.csl.2021.101197)**Ning Gong, Nianmin Yao, Ziying Lv et al.*1 citation*
91. **[Glimpse-based estimation of speech intelligibility from speech-in-noise using artificial neural networks ↗](https://doi.org/10.1016/j.csl.2021.101220)**Yan Mei Tang*1 citation*
92. **[Towards sound based testing of COVID-19—Summary of the first Diagnostics of COVID-19 using Acoustics (DiCOVA) Challenge ↗](https://doi.org/10.1016/j.csl.2021.101320)**Neeraj Kumar Sharma, Ananya Muguli, Prashant Krishnan et al.*1 citation*
93. **[Unsupervised induction of inflectional families ↗](https://doi.org/10.1016/j.csl.2021.101324)**Amit Kirschenbaum*1 citation*
94. **[Adaptive line enhancer for nonstationary harmonic noise reduction ↗](https://doi.org/10.1016/j.csl.2021.101245)**Aviva Atkins, Israel Cohen, Jacob Benesty
95. **[Joint speaker separation and recognition using non-negative matrix deconvolution with adaptive dictionary ↗](https://doi.org/10.1016/j.csl.2021.101223)**Szymon Drgas, Tuomas I. Virtanen
- [← back to](https://md.research.elamur.ai/free/en/venues/computer-speech-language/2021/) — Computer Speech & Language 2021