---
title: "Interspeech 2021 — all accepted papers, page 4"
description: "All 963 papers of Interspeech 2021 · page 4 of 10, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/4/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/4/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Interspeech](https://md.research.elamur.ai/free/en/venues/interspeech-usb/) / [2021](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/) / [papers](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/) / page 4

# Interspeech 2021: all accepted papers

963 papers · page 4 of 10 · the most cited first · [← Interspeech 2021](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/)

[← prev](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/3/) [1](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/) [2](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/2/) [3](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/3/) **4** [5](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/5/) … [10](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/10/) [next →](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/5/)

301. **[FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-866)**Taejun Bak, Jae-Sung Bae, Hanbin Bae et al.*12 citations*
302. **[Hierarchical Phone Recognition with Compositional Phonetics ↗](https://doi.org/10.21437/interspeech.2021-1803)**Xinjian Li, Juncheng Li, Florian Metze et al.*12 citations*
303. **[Layer Pruning on Demand with Intermediate CTC ↗](https://doi.org/10.21437/interspeech.2021-1171)**Jaesong Lee, Jingu Kang, Shinji Watanabe*12 citations*
304. **[Lightweight Causal Transformer with Local Self-Attention for Real-Time Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-668)**Koen Oostermeijer, Qing Wang, Jun Du*12 citations*
305. **[Multimodal Speech Summarization Through Semantic Concept Learning ↗](https://doi.org/10.21437/interspeech.2021-1923)**Shruti Palaskar, Ruslan Salakhutdinov, Alan W. Black et al.*12 citations*
306. **[Online Compressive Transformer for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-545)**Chi-Hang Leong, Yu-Han Huang, Jen‐Tzung Chien*12 citations*
307. **[Personalized Keyphrase Detection Using Speaker and Environment Information ↗](https://doi.org/10.21437/interspeech.2021-204)**Rajeev Vijay Rikhye, Quan Wang, Qiao Liang et al.*12 citations*
308. **[Robust Continuous On-Device Personalization for Automatic Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-318)**Khe Chai Sim, Angad Chandorkar, Fan Gao et al.*12 citations*
309. **[RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-341)**Rohola Zandie, Mohammad H. Mahoor, Julia Madsen et al.*12 citations*
310. **[Semi-Supervised Training with Pseudo-Labeling for End-To-End Neural Diarization ↗](https://doi.org/10.21437/interspeech.2021-384)**Yuki Takashima, Yusuke Fujita, Shota Horiguchi et al.*12 citations*
311. **[Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation ↗](https://doi.org/10.21437/interspeech.2021-677)**Zhehuai Chen, Andrew Rosenberg, Yu Zhang et al.*12 citations*
312. **[Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021 ↗](https://doi.org/10.21437/interspeech.2021-1503)**Takashi Maekaku, Xuankai Chang, Yuya Fujita et al.*12 citations*
313. **[Speech2Video: Cross-Modal Distillation for Speech to Video Generation ↗](https://doi.org/10.21437/interspeech.2021-1996)**Shijing Si, Jianzong Wang, Xiaoyang Qu et al.*12 citations*
314. **[Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-173)**Xurong Xie, Rukiye Ruzi, Xunying Liu et al.*12 citations*
315. **[Visual Transformers for Primates Classification and Covid Detection ↗](https://doi.org/10.21437/interspeech.2021-273)**Steffen Illium, Robert Müller, Andreas Sedlmeier et al.*12 citations*
316. **[Acoustic Event Detection with Classifier Chains ↗](https://doi.org/10.21437/interspeech.2021-2218)**Tatsuya Komatsu, Shinji Watanabe, Koichi Miyazaki et al.*11 citations*
317. **[Adapting Long Context NLM for ASR Rescoring in Conversational Agents ↗](https://doi.org/10.21437/interspeech.2021-1849)**Ashish Shenoy, Sravan Bodapati, Monica Sunkara et al.*11 citations*
318. **[Adaptive Margin Circle Loss for Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-1043)**Runqiu Xiao, Xiaoxiao Miao, Wenchao Wang et al.*11 citations*
319. **[Align-Denoise: Single-Pass Non-Autoregressive Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1906)**Nanxin Chen, Piotr Żelasko, Laureano Moro-Velázquez et al.*11 citations*
320. **[AlloST: Low-Resource Speech Translation Without Source Transcription ↗](https://doi.org/10.21437/interspeech.2021-526)**Yao-Fei Cheng, Hung-Shin Lee, Hsin‐Min Wang*11 citations*
321. **[Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input ↗](https://doi.org/10.21437/interspeech.2021-275)**Brooke Stephenson, Thomas Hueber, Laurent Girin B et al.*11 citations*
322. **[An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation ↗](https://doi.org/10.21437/interspeech.2021-1253)**Xiangheng He, Junjie Chen, Georgios Rizos et al.*11 citations*
323. **[Attention-Based Keyword Localisation in Speech Using Visual Grounding ↗](https://doi.org/10.21437/interspeech.2021-435)**Kayode Olaleye, Herman Kamper*11 citations*
324. **[Bayesian Parametric and Architectural Domain Adaptation of LF-MMI Trained TDNNs for Elderly and Dysarthric Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-289)**Jiajun Deng, Fabian Ritter-Gutierrez, Shoukang Hu et al.*11 citations*
325. **[Binary Neural Network for Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-600)**Tinglong Zhu, Xiaoyi Qin, Ming Li*11 citations*
326. **[CVC: Contrastive Learning for Non-Parallel Voice Conversion ↗](https://doi.org/10.21437/interspeech.2021-137)**Tingle Li, Yichen Liu, Chenxu Hu et al.*11 citations*
327. **[CoDERT: Distilling Encoder Representations with Co-Learning for Transducer-Based Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-797)**Rupak Vignesh Swaminathan, Brian King, Grant P. Strimel et al.*11 citations*
328. **[Cross-Lingual Low Resource Speaker Adaptation Using Phonological Features ↗](https://doi.org/10.21437/interspeech.2021-327)**Georgia Maniati, Nikolaos Ellinas, Κωνσταντίνος Μαρκόπουλος et al.*11 citations*
329. **[DBNet: A Dual-Branch Network Architecture Processing on Spectrum and Waveform for Single-Channel Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-1042)**Kanghao Zhang, Shulin He, Hao Li et al.*11 citations*
330. **[Data Augmentation Methods for End-to-End Speech Recognition on Distant-Talk Scenarios ↗](https://doi.org/10.21437/interspeech.2021-958)**Emiru Tsunoo, Kentaro Shibata, Chaitanya Prasad Narisetty et al.*11 citations*
331. **[Deep Feature CycleGANs: Speaker Identity Preserving Non-Parallel Microphone-Telephone Domain Adaptation for Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-1502)**Saurabh Kataria, Jesús Villalba, Piotr Żelasko et al.*11 citations*
332. **[Dual Script E2E Framework for Multilingual and Code-Switching ASR ↗](https://doi.org/10.21437/interspeech.2021-978)**Mari Ganesh Kumar, Jom Kuriakose, Anand Thyagachandran et al.*11 citations*
333. **[Emotion Carrier Recognition from Personal Narratives ↗](https://doi.org/10.21437/interspeech.2021-1100)**Aniruddha Tammewar, Alessandra Cervone, Giuseppe Riccardi*11 citations*
334. **[Emotional Prosody Control for Speech Generation ↗](https://doi.org/10.21437/interspeech.2021-307)**Sarath Sivaprasad, Saiteja Kosgi, Vineet Gandhi*11 citations*
335. **[End-to-End Spelling Correction Conditioned on Acoustic Feature for Code-Switching Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1242)**Shuai Zhang, Jiangyan Yi, Zhengkun Tian et al.*11 citations*
336. **[FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization ↗](https://doi.org/10.21437/interspeech.2021-1367)**Zhengkun Tian, Jiangyan Yi, Ye Bai et al.*11 citations*
337. **[Federated Learning with Dynamic Transformer for Text to Speech ↗](https://doi.org/10.21437/interspeech.2021-2039)**Zhenhou Hong, Jianzong Wang, Xiaoyang Qu et al.*11 citations*
338. **[Funnel Deep Complex U-Net for Phase-Aware Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-10)**Yuhang Sun, Linju Yang, Huifeng Zhu et al.*11 citations*
339. **[Investigation of Practical Aspects of Single Channel Speech Separation for ASR ↗](https://doi.org/10.21437/interspeech.2021-921)**Jian Wu, Zhuo Chen, Sanyuan Chen et al.*11 citations*
340. **[Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-964)**Guodong Ma, Pengfei Hu, Jian Kang et al.*11 citations*
341. **[Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End ↗](https://doi.org/10.21437/interspeech.2021-836)**Swayambhu Nath Ray, Minhua Wu, Anirudh Raju et al.*11 citations*
342. **[Many-to-Many Voice Conversion Based Feature Disentanglement Using Variational Autoencoder ↗](https://doi.org/10.21437/interspeech.2021-2086)**Manh Luong, Viet Anh Tran*11 citations*
343. **[Microphone Array Generalization for Multichannel Narrowband Deep Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-944)**Siyuan Zhang, Xiaofei Li*11 citations*
344. **[Modeling and Training Strategies for Language Recognition Systems ↗](https://doi.org/10.21437/interspeech.2021-277)**Raphaël Duroselle, Md Sahidullah, Denis Jouvet et al.*11 citations*
345. **[Reinforce-Aligner: Reinforcement Alignment Search for Robust End-to-End Text-to-Speech ↗](https://doi.org/10.21437/interspeech.2021-831)**Hyunseung Chung, Sanghoon Lee, Seong–Whan Lee*11 citations*
346. **[Speech Emotion Recognition via Multi-Level Cross-Modal Distillation ↗](https://doi.org/10.21437/interspeech.2021-785)**Ruichen Li, Jinming Zhao, Qin Jin*11 citations*
347. **[Unified Source-Filter GAN: Unified Source-Filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN ↗](https://doi.org/10.21437/interspeech.2021-517)**Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda*11 citations*
348. **[Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding ↗](https://doi.org/10.21437/interspeech.2021-1843)**Heting Gao, Junrui Ni, Yang Zhang et al.*11 citations*
349. **[A Spectro-Temporal Glimpsing Index (STGI) for Speech Intelligibility Prediction ↗](https://doi.org/10.21437/interspeech.2021-605)**Amin Edraki, Wai-Yip Chan, Jesper Jensen et al.*10 citations*
350. **[Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1623)**Wei Guo Zhou, Mohammad Zeineldeen, Zuoyun Zheng et al.*10 citations*
351. **[Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-Based Multimodal Fusion ↗](https://doi.org/10.21437/interspeech.2021-80)**Baptiste Pouthier, Laurent Pilati, Leela K. Gudupudi et al.*10 citations*
352. **[Annotation Confidence vs. Training Sample Size: Trade-Off Solution for Partially-Continuous Categorical Emotion Recognition ↗](https://doi.org/10.21437/interspeech.2021-1636)**Елена Витальевна Рюмина, Oxana Verkholyak, Alexey Anatolievich Karpov*10 citations*
353. **[Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition ↗](https://doi.org/10.21437/interspeech.2021-2173)**Zhengxi Liu, Yanmin Qian*10 citations*
354. **[Conformer Parrotron: A Faster and Stronger End-to-End Speech Conversion and Recognition Model for Atypical Speech ↗](https://doi.org/10.21437/interspeech.2021-676)**Zhehuai Chen, Bhuvana Ramabhadran, Fadi Biadsy et al.*10 citations*
355. **[Continuous Speech Separation Using Speaker Inventory for Long Recording ↗](https://doi.org/10.21437/interspeech.2021-338)**Cong Han, Yi Luo, Chenda Li et al.*10 citations*
356. **[Diagnosis of COVID-19 Using Auditory Acoustic Cues ↗](https://doi.org/10.21437/interspeech.2021-497)**Rohan Kumar Das, Maulik C. Madhavi, Haizhou Li*10 citations*
357. **[Domain-Aware Self-Attention for Multi-Domain Neural Machine Translation ↗](https://doi.org/10.21437/interspeech.2021-1477)**Shiqi Zhang, Yan Liu, Deyi Xiong et al.*10 citations*
358. **[End-to-End Spoken Language Understanding for Generalized Voice Assistants ↗](https://doi.org/10.21437/interspeech.2021-1826)**Michael Saxon, Samridhi Choudhary, Joseph P. McKenna et al.*10 citations*
359. **[Exploring Emotional Prototypes in a High Dimensional TTS Latent Space ↗](https://doi.org/10.21437/interspeech.2021-1538)**Pol van Rijn, Silvan Mertes, Dominik Schiller et al.*10 citations*
360. **[Fine-Grained Prosody Modeling in Neural Speech Synthesis Using ToBI Representation ↗](https://doi.org/10.21437/interspeech.2021-883)**Yuxiang Zou, Shichao Liu, Xiang Yin et al.*10 citations*
361. **[Generalized Dilated CNN Models for Depression Detection Using Inverted Vocal Tract Variables ↗](https://doi.org/10.21437/interspeech.2021-1960)**Nadee Seneviratne, Carol Espy-Wilson*10 citations*
362. **[Improve Cross-Lingual Text-To-Speech Synthesis on Monolingual Corpora with Pitch Contour Information ↗](https://doi.org/10.21437/interspeech.2021-474)**Haoyue Zhan, Haitong Zhang, Wenjie Ou et al.*10 citations*
363. **[Improving Customization of Neural Transducers by Mitigating Acoustic Mismatch of Synthesized Audio ↗](https://doi.org/10.21437/interspeech.2021-1656)**Gakuto Kurata, George Saon, Brian E. D. Kingsbury et al.*10 citations*
364. **[Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss ↗](https://doi.org/10.21437/interspeech.2021-1410)**Xu Zhang, Xinlei Ren, Xiguang Zheng et al.*10 citations*
365. **[MIMO Self-Attentive RNN Beamformer for Multi-Speaker Speech Separation ↗](https://doi.org/10.21437/interspeech.2021-570)**Xiyun Li, Yong Xu, Yu Meng et al.*10 citations*
366. **[Metric Learning Based Feature Representation with Gated Fusion Model for Speech Emotion Recognition ↗](https://doi.org/10.21437/interspeech.2021-1133)**Yuan Gao, Jiaxing Liu, Longbiao Wang et al.*10 citations*
367. **[Pairing Weak with Strong: Twin Models for Defending Against Adversarial Attack on Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-1343)**Zhiyuan Peng, Xu Li, Tan Lee*10 citations*
368. **[Phrase Break Prediction with Bidirectional Encoder Representations in Japanese Text-to-Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-252)**Kosuke Futamata, Byeongseon Park, Ryuichi Yamamoto et al.*10 citations*
369. **[Real-Time Speaker Counting in a Cocktail Party Scenario Using Attention-Guided Convolutional Neural Network ↗](https://doi.org/10.21437/interspeech.2021-331)**Midia Yousefi, John H. L. Hansen*10 citations*
370. **[Reducing Streaming ASR Model Delay with Self Alignment ↗](https://doi.org/10.21437/interspeech.2021-322)**Jaeyoung Kim, Han Lu, Anshuman Tripathi et al.*10 citations*
371. **[Representation Learning to Classify and Detect Adversarial Attacks Against Speaker and Speech Recognition Systems ↗](https://doi.org/10.21437/interspeech.2021-1759)**Jesús Villalba, Sonal Joshi, Piotr Żelasko et al.*10 citations*
372. **[Residual Energy-Based Models for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-690)**Qiujia Li, Yu Zhang, Bo Li et al.*10 citations*
373. **[Robust Command Recognition for Lithuanian Air Traffic Control Tower Utterances ↗](https://doi.org/10.21437/interspeech.2021-935)**Oliver Ohneiser, Seyyed Saeed Sarfjoo, Hartmut Helmke et al.*10 citations*
374. **[Scaling Sparsemax Based Channel Selection for Speech Recognition with ad-hoc Microphone Arrays ↗](https://doi.org/10.21437/interspeech.2021-419)**Junqi Chen, Xiao-Lei Zhang*10 citations*
375. **[Speaking with a KN95 Face Mask: ASR Performance and Speaker Compensation ↗](https://doi.org/10.21437/interspeech.2021-99)**Sarah E. Gutz, Hannah P. Rowe, Jordan R. Green*10 citations*
376. **[Streaming Multi-Talker Speech Recognition with Joint Speaker Identification ↗](https://doi.org/10.21437/interspeech.2021-207)**Liang Lu, Naoyuki Kanda, Jinyu Li et al.*10 citations*
377. **[Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation ↗](https://doi.org/10.21437/interspeech.2021-1428)**Vineet Garg, Wonil Chang, Siddharth Sigtia et al.*10 citations*
378. **[Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification ↗](https://doi.org/10.21437/interspeech.2021-300)**Dongchao Yang, Helin Wang, Yuexian Zou*10 citations*
379. **[Variational Information Bottleneck for Effective Low-Resource Audio Classification ↗](https://doi.org/10.21437/interspeech.2021-2028)**Shijing Si, Jianzong Wang, Huiming Sun et al.*10 citations*
380. **[Voice Privacy Through x-Vector and CycleGAN-Based Anonymization ↗](https://doi.org/10.21437/interspeech.2021-1573)**Gauri P. Prajapati, Dipesh K. Singh, Preet P. Amin et al.*10 citations*
381. **[A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-775)**Shigeki Karita, Yotaro Kubo, Michiel Bacchiani et al.*9 citations*
382. **[Acted vs. Improvised: Domain Adaptation for Elicitation Approaches in Audio-Visual Emotion Recognition ↗](https://doi.org/10.21437/interspeech.2021-666)**Haoqi Li, Yelin Kim, Cheng-Hao Kuo et al.*9 citations*
383. **[Audio-Visual Multi-Talker Speech Recognition in a Cocktail Party ↗](https://doi.org/10.21437/interspeech.2021-2128)**Yifei Wu, Chenda Li, Song Yang et al.*9 citations*
384. **[Audio-Visual Recognition of Emotional Engagement of People with Dementia ↗](https://doi.org/10.21437/interspeech.2021-567)**Lars Steinert, Felix Putze, Dennis Küster et al.*9 citations*
385. **[Automatic Severity Classification of Korean Dysarthric Speech Using Phoneme-Level Pronunciation Features ↗](https://doi.org/10.21437/interspeech.2021-1353)**Eun Jung Yeo, Sunhee Kim, Minhwa Chung*9 citations*
386. **[Confidence Intervals for ASR-Based TTS Evaluation ↗](https://doi.org/10.21437/interspeech.2021-2203)**Jason Taylor, Korin Richmond*9 citations*
387. **[Contrastive Learning of Cough Descriptors for Automatic COVID-19 Preliminary Diagnosis ↗](https://doi.org/10.21437/interspeech.2021-1249)**Swapnil Bhosale, Upasana Tiwari, Rupayan Chakraborty et al.*9 citations*
388. **[Cross-Lingual Speaker Adaptation Using Domain Adaptation and Speaker Consistency Loss for Text-To-Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-897)**Detai Xin, Yuki Saito, Shinnosuke Takamichi et al.*9 citations*
389. **[Development of a Psychoacoustic Loss Function for the Deep Neural Network (DNN)-Based Speech Coder ↗](https://doi.org/10.21437/interspeech.2021-2151)**Joon Byun, Seungmin Shin, Young-Cheol Park et al.*9 citations*
390. **[Direct Multimodal Few-Shot Learning of Speech and Images ↗](https://doi.org/10.21437/interspeech.2021-49)**Leanne Nortje, Herman Kamper*9 citations*
391. **[Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency ↗](https://doi.org/10.21437/interspeech.2021-1272)**Yangyang Shi, Varun Nagaraja, Chunyang Wu et al.*9 citations*
392. **[High-Fidelity Parallel WaveGAN with Multi-Band Harmonic-Plus-Noise Model ↗](https://doi.org/10.21437/interspeech.2021-976)**Min-Jae Hwang, Ryuichi Yamamoto, Eunwoo Song et al.*9 citations*
393. **[High-Fidelity and Low-Latency Universal Neural Vocoder Based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling ↗](https://doi.org/10.21437/interspeech.2021-1984)**Patrick Lumban Tobing, Tomoki Toda*9 citations*
394. **[Improving RNN-T for Domain Scaling Using Semi-Supervised Training with Neural TTS ↗](https://doi.org/10.21437/interspeech.2021-1017)**Yan Deng, Rui Zhao, Zhong Meng et al.*9 citations*
395. **[Improving Weakly Supervised Sound Event Detection with Self-Supervised Auxiliary Tasks ↗](https://doi.org/10.21437/interspeech.2021-2079)**Soham Deshmukh, Bhiksha Raj, Rita Singh*9 citations*
396. **[Incorporating Embedding Vectors from a Human Mean-Opinion Score Prediction Model for Monaural Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-1844)**Khandokar Md. Nayem, Donald S. Williamson*9 citations*
397. **[Incorporating External POS Tagger for Punctuation Restoration ↗](https://doi.org/10.21437/interspeech.2021-1708)**Ning Shi, Wei Wang, Boxin Wang et al.*9 citations*
398. **[Multi-Stage Progressive Speech Enhancement Network ↗](https://doi.org/10.21437/interspeech.2021-520)**Xinmeng Xu, Yang Wang, Dongxiang Xu et al.*9 citations*
399. **[Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction ↗](https://doi.org/10.21437/interspeech.2021-1207)**David Qiu, Yanzhang He, Qiujia Li et al.*9 citations*
400. **[Multilingual Transfer of Acoustic Word Embeddings Improves When Training on Languages Related to the Target Zero-Resource Language ↗](https://doi.org/10.21437/interspeech.2021-461)**Christiaan Jacobs, Herman Kamper*9 citations*

[← prev](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/3/) [1](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/) [2](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/2/) [3](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/3/) **4** [5](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/5/) … [10](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/10/) [next →](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/5/)

- [← back to](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/) — Interspeech 2021