---
title: "Interspeech 2021 — all accepted papers, page 5"
description: "All 963 papers of Interspeech 2021 · page 5 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/5/"
---
[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/5/)

[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 5

# Interspeech 2021: all accepted papers

963 papers · page 5 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/4/) [1](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/) … [4](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/4/) **5** [6](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/6/) … [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/6/)

401. **[Multitask Training with Text Data for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-683)**Peidong Wang, Tara N. Sainath, Ron J. Weiss*9 citations*
402. **[Non-Intrusive Speech Quality Assessment with Transfer Learning and Subject-Specific Scaling ↗](https://doi.org/10.21437/interspeech.2021-1685)**Natalia Nessler, Miloš Cerňak, Paolo Prandoni et al.*9 citations*
403. **[On the Learning Dynamics of Semi-Supervised Training for ASR ↗](https://doi.org/10.21437/interspeech.2021-1777)**Electra Wallington, Benji Kershenbaum, Ondřej Klejch et al.*9 citations*
404. **[One Size Does Not Fit All in Resource-Constrained ASR ↗](https://doi.org/10.21437/interspeech.2021-1970)**Ethan Morris, Robbie Jimerson, Emily Tucker Prud’hommeaux*9 citations*
405. **[Optimising Hearing Aid Fittings for Speech in Noise with a Differentiable Hearing Loss Model ↗](https://doi.org/10.21437/interspeech.2021-1613)**Zehai Tu, Ning Ma, Jon Barker*9 citations*
406. **[Recognising Covid-19 from Coughing Using Ensembles of SVMs and LSTMs with Handcrafted and Deep Audio Features ↗](https://doi.org/10.21437/interspeech.2021-1267)**Vincent Karas, Björn Wolfgang Schuller*9 citations*
407. **[Remote Smartphone-Based Speech Collection: Acceptance and Barriers in Individuals with Major Depressive Disorder ↗](https://doi.org/10.21437/interspeech.2021-1240)**Judith Dineley, Grace Lavelle, Daniel Leightley et al.*9 citations*
408. **[Revisiting Parity of Human vs. Machine Conversational Speech Transcription ↗](https://doi.org/10.21437/interspeech.2021-1908)**Courtney Mansfield, Sara Ng, Gina‐Anne Levow et al.*9 citations*
409. **[Synthesis of Expressive Speaking Styles with Limited Training Data in a Multi-Speaker, Prosody-Controllable Sequence-to-Sequence Architecture ↗](https://doi.org/10.21437/interspeech.2021-1446)**Slava Shechtman, Raul Fernandez, Alexander S. Sorin et al.*9 citations*
410. **[Talk, Don’t Write: A Study of Direct Speech-Based Image Retrieval ↗](https://doi.org/10.21437/interspeech.2021-96)**Ramon Sanabria, Austin Waters, Jason Baldridge*9 citations*
411. **[TalkNet: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-1770)**Stanislav Beliaev, Boris Ginsburg*9 citations*
412. **[TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation ↗](https://doi.org/10.21437/interspeech.2021-481)**Helin Wang, Bo Wu, Lianwu Chen et al.*9 citations*
413. **[Time-Frequency Representation Learning with Graph Convolutional Network for Dialogue-Level Speech Emotion Recognition ↗](https://doi.org/10.21437/interspeech.2021-2067)**Jiaxing Liu, Yaodong Song, Longbiao Wang et al.*9 citations*
414. **[Transformer-Based Acoustic Modeling for Streaming Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-1655)**Chunyang Wu, Zhiping Xiu, Yangyang Shi et al.*9 citations*
415. **[VAENAR-TTS: Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-2121)**Hui Lu, Zhiyong Wu, Xixin Wu et al.*9 citations*
416. **[A Hands-On Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation ↗](https://doi.org/10.21437/interspeech.2021-1418)**Martin Strauss, Jouni Paulus, Matteo Torcoli et al.*8 citations*
417. **[A Study into Pre-Training Strategies for Spoken Language Understanding on Dysarthric Speech ↗](https://doi.org/10.21437/interspeech.2021-1720)**Pu Wang, Bagher BabaAli, Hugo Van hamme*8 citations*
418. **[Age-Invariant Training for End-to-End Child Speech Recognition Using Adversarial Multi-Task Learning ↗](https://doi.org/10.21437/interspeech.2021-1241)**Lars Rumberg, Hanna Ehlert, Ulrike M. Lüdtke et al.*8 citations*
419. **[Auto-KWS 2021 Challenge: Task, Datasets, and Baselines ↗](https://doi.org/10.21437/interspeech.2021-817)**Jingsong Wang, Yuxuan He, Chunyu Zhao et al.*8 citations*
420. **[Automatically Detecting Errors and Disfluencies in Read Speech to Predict Cognitive Impairment in People with Parkinson’s Disease ↗](https://doi.org/10.21437/interspeech.2021-1694)**Amrit Romana, John Bandon, Matthew C Perez et al.*8 citations*
421. **[Bidirectional Multiscale Feature Aggregation for Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-111)**Jiajun Qi, Wu Guo, Bin Gu*8 citations*
422. **[Bootstrap an End-to-End ASR System by Multilingual Training, Transfer Learning, Text-to-Text Mapping and Synthetic Audio ↗](https://doi.org/10.21437/interspeech.2021-198)**Manuel Giollo, Deniz Gunceler, Yulan Liu et al.*8 citations*
423. **[Communication-Efficient Agnostic Federated Averaging ↗](https://doi.org/10.21437/interspeech.2021-153)**Jae Hun Ro, Mingqing Chen, Rajiv Mathews et al.*8 citations*
424. **[Discriminative Self-Training for Punctuation Prediction ↗](https://doi.org/10.21437/interspeech.2021-246)**Qian Chen, Wen Wang, Mengzhe Chen et al.*8 citations*
425. **[ETLT 2021: Shared Task on Automatic Speech Recognition for Non-Native Children’s Speech ↗](https://doi.org/10.21437/interspeech.2021-1237)**Roberto Gretter, Marco Matassoni, Daniele Falavigna et al.*8 citations*
426. **[Enrollment-Less Training for Personalized Voice Activity Detection ↗](https://doi.org/10.21437/interspeech.2021-731)**Naoki Makishima, Mana Ihori, Tomohiro Tanaka et al.*8 citations*
427. **[Estimating Articulatory Movements in Speech Production with Transformer Networks ↗](https://doi.org/10.21437/interspeech.2021-1375)**Sathvik Udupa, Anwesha Roy, Abhayjeet Singh et al.*8 citations*
428. **[Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization ↗](https://doi.org/10.21437/interspeech.2021-1905)**Gonçal V. Garcés Díaz-Munío, Joan Albert Silvestre-Cerdà, Javier Jorge et al.*8 citations*
429. **[Factorization-Aware Training of Transformers for Natural Language Understanding on the Edge ↗](https://doi.org/10.21437/interspeech.2021-1816)**Hamidreza Saghir, Samridhi Choudhary, Sepehr Eghbali et al.*8 citations*
430. **[Fearless Steps Challenge Phase-3 (FSC P3): Advancing SLT for Unseen Channel and Mission Data Across NASA Apollo Audio ↗](https://doi.org/10.21437/interspeech.2021-2011)**Aditya Joglekar, Seyed Omid Sadjadi, Meena Chandra-Shekar et al.*8 citations*
431. **[Identifying Cognitive Impairment Using Sentence Representation Vectors ↗](https://doi.org/10.21437/interspeech.2021-915)**Bahman Mirheidari, Yilin Pan, Daniel J. Blackburn et al.*8 citations*
432. **[Identifying Conflict Escalation and Primates by Using Ensemble X-Vectors and Fisher Vector Features ↗](https://doi.org/10.21437/interspeech.2021-1173)**José Vicente Egas-López, Mercedes Vetráb, László Tóth et al.*8 citations*
433. **[Know Your Enemy, Know Yourself: A Unified Two-Stage Framework for Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-238)**Wenzhe Liu, Andong Li, Yuxuan Ke et al.*8 citations*
434. **[LACOPE: Latency-Constrained Pitch Estimation for Speech Enhancement ↗](https://doi.org/10.21437/interspeech.2021-633)**Hendrik Schröter, Tobias Rosenkranz, Alberto N. Escalante-B. et al.*8 citations*
435. **[Language Recognition on Unknown Conditions: The LORIA-Inria-MULTISPEECH System for AP20-OLR Challenge ↗](https://doi.org/10.21437/interspeech.2021-276)**Raphaël Duroselle, Md Sahidullah, Denis Jouvet et al.*8 citations*
436. **[Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion ↗](https://doi.org/10.21437/interspeech.2021-285)**Disong Wang, Songxiang Liu, Lifa Sun et al.*8 citations*
437. **[Lookup-Table Recurrent Language Models for Long Tail Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-340)**Wei‐Chin Huang, Tara N. Sainath, Cal Peyser et al.*8 citations*
438. **[M3: MultiModal Masking Applied to Sentiment Analysis ↗](https://doi.org/10.21437/interspeech.2021-1739)**Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos*8 citations*
439. **[Multiple Softmax Architecture for Streaming Multilingual End-to-End ASR Systems ↗](https://doi.org/10.21437/interspeech.2021-1298)**Vikas Joshi, Amit Kumar Das, Eric Sun et al.*8 citations*
440. **[Oriental Language Recognition (OLR) 2020: Summary and Analysis ↗](https://doi.org/10.21437/interspeech.2021-2171)**Jing Li, Binling Wang, Yiming Zhi et al.*8 citations*
441. **[Phoneme-Aware and Channel-Wise Attentive Learning for Text Dependent Speaker Verification ↗](https://doi.org/10.21437/interspeech.2021-2137)**Yan Liu, Zheng Li, Lin Li et al.*8 citations*
442. **[Phonetically Motivated Self-Supervised Speech Representation Learning ↗](https://doi.org/10.21437/interspeech.2021-905)**Xianghu Yue, Haizhou Li*8 citations*
443. **[RaSSpeR: Radar-Based Silent Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1413)**David Ferreira, Samuel Silva, Francisco Curado et al.*8 citations*
444. **[Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding ↗](https://doi.org/10.21437/interspeech.2021-1537)**Siddhant Arora, Alissa Ostapenko, Vijay Viswanathan et al.*8 citations*
445. **[Scaling Laws for Acoustic Models ↗](https://doi.org/10.21437/interspeech.2021-1644)**Jasha Droppo, Oğuz H. Elibol*8 citations*
446. **[Single-Channel Speech Enhancement Using Learnable Loss Mixup ↗](https://doi.org/10.21437/interspeech.2021-859)**Oscar Chang, Dung N. Tran, Kazuhito Koishida*8 citations*
447. **[SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction ↗](https://doi.org/10.21437/interspeech.2021-733)**Junkun Chen, Mingbo Ma, Renjie Zheng et al.*8 citations*
448. **[Speech Denoising with Auditory Models ↗](https://doi.org/10.21437/interspeech.2021-1973)**Mark R. Saddler, Andrew Francl, Jenelle Feather et al.*8 citations*
449. **[Spine2Net: SpineNet with Res2Net and Time-Squeeze-and-Excitation Blocks for Speaker Recognition ↗](https://doi.org/10.21437/interspeech.2021-1163)**Magdalena Rybicka, Jesús Villalba, Piotr Żelasko et al.*8 citations*
450. **[Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training ↗](https://doi.org/10.21437/interspeech.2021-763)**Sung-Feng Huang, Shun-Po Chuang, Da-Rong Liu et al.*8 citations*
451. **[The CSTR System for Multilingual and Code-Switching ASR Challenges for Low Resource Indian Languages ↗](https://doi.org/10.21437/interspeech.2021-1035)**Ondřej Klejch, Electra Wallington, Peter Bell*8 citations*
452. **[Weakly Supervised Construction of ASR Systems from Massive Video Data ↗](https://doi.org/10.21437/interspeech.2021-7)**Mengli Cheng, Chengyu Wang, Jun Huang et al.*8 citations*
453. **[Zero-Shot Federated Learning with New Classes for Audio Classification ↗](https://doi.org/10.21437/interspeech.2021-2264)**Gautham Krishna Gudur, Satheesh Kumar Perepu*8 citations*
454. **[A Benchmark of Dynamical Variational Autoencoders Applied to Speech Spectrogram Modeling ↗](https://doi.org/10.21437/interspeech.2021-256)**Xiaoyu Bie, Laurent Girin B, Simon Leglaive et al.*7 citations*
455. **[A Lightweight Framework for Online Voice Activity Detection in the Wild ↗](https://doi.org/10.21437/interspeech.2021-1977)**Xuenan Xu, Heinrich Dinkel, Mengyue Wu et al.*7 citations*
456. **[A Universal Multi-Speaker Multi-Style Text-to-Speech via Disentangled Representation Learning Based on Rényi Divergence Minimization ↗](https://doi.org/10.21437/interspeech.2021-660)**Dipjyoti Paul, Sankar Mukherjee, Yannis Pantazis et al.*7 citations*
457. **[Additive Phoneme-Aware Margin Softmax Loss for Language Recognition ↗](https://doi.org/10.21437/interspeech.2021-1167)**Zheng Li, Yan Liu, Lin Li et al.*7 citations*
458. **[An Effective Mutual Mean Teaching Based Domain Adaptation Method for Sound Event Detection ↗](https://doi.org/10.21437/interspeech.2021-281)**Xu Zheng, Yan Song, Li-Rong Dai et al.*7 citations*
459. **[Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit ↗](https://doi.org/10.21437/interspeech.2021-303)**Einari Vaaras, Sari Ahlqvist‐Björkroth, Konstantinos Drossos et al.*7 citations*
460. **[Auxiliary Loss Function for Target Speech Extraction and Recognition with Weak Supervision Based on Speaker Characteristics ↗](https://doi.org/10.21437/interspeech.2021-986)**Kateřina Žmolíková, Marc Delcroix, Desh Raj et al.*7 citations*
461. **[Binaural Speech Separation of Moving Speakers With Preserved Spatial Cues ↗](https://doi.org/10.21437/interspeech.2021-1372)**Cong Han, Yi Luo, Nima Mesgarani*7 citations*
462. **[CLAC: A Speech Corpus of Healthy English Speakers ↗](https://doi.org/10.21437/interspeech.2021-1810)**R’mani Haulcy, James Glass*7 citations*
463. **[CNN-Based Processing of Acoustic and Radio Frequency Signals for Speaker Localization from MAVs ↗](https://doi.org/10.21437/interspeech.2021-886)**Andrea Toma, Daniele Salvati, Carlo Drioli et al.*7 citations*
464. **[Collaborative Training of Acoustic Encoders for Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-354)**Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh et al.*7 citations*
465. **[Comparison of Remote Experiments Using Crowdsourcing and Laboratory Experiments on Speech Intelligibility ↗](https://doi.org/10.21437/interspeech.2021-174)**Ayako Yamamoto, Toshio Irino, Kenichi Arai et al.*7 citations*
466. **[Continuous Wavelet Vocoder-Based Decomposition of Parametric Speech Waveform Synthesis ↗](https://doi.org/10.21437/interspeech.2021-1600)**Mohammed Salah Al-Radhi, Tamás Gábor Csapó, Csaba Zainkó et al.*7 citations*
467. **[Cross-Modal Learning for Audio-Visual Video Parsing ↗](https://doi.org/10.21437/interspeech.2021-2135)**Jatin Lamba, - Abhishek, Jayaprakash Akula et al.*7 citations*
468. **[Detection and Analysis of Attention Errors in Sequence-to-Sequence Text-to-Speech ↗](https://doi.org/10.21437/interspeech.2021-286)**Cassia Valentini-Botinhao, Simon King*7 citations*
469. **[Differentiable Allophone Graphs for Language-Universal Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1944)**Brian Yan, Siddharth Dalmia, David R. Mortensen et al.*7 citations*
470. **[Dynamic Multi-Scale Convolution for Dialect Identification ↗](https://doi.org/10.21437/interspeech.2021-56)**Tianlong Kong, Shouyi Yin, Dawei Zhang et al.*7 citations*
471. **[Dynamically Adaptive Machine Speech Chain Inference for TTS in Noisy Environment: Listen and Speak Louder ↗](https://doi.org/10.21437/interspeech.2021-946)**Sashi Novitasari, Sakriani Sakti, Satoshi Nakamura*7 citations*
472. **[End-to-End Open Vocabulary Keyword Search ↗](https://doi.org/10.21437/interspeech.2021-1399)**Bolaji Yusuf, Alican Gök, Batuhan Gündoğdu et al.*7 citations*
473. **[FANS: Fusing ASR and NLU for On-Device SLU ↗](https://doi.org/10.21437/interspeech.2021-793)**Martin Radfar, Athanasios Mouchtaris, Siegfried Kunzmann et al.*7 citations*
474. **[Improving Multi-Speaker TTS Prosody Variance with a Residual Encoder and Normalizing Flows ↗](https://doi.org/10.21437/interspeech.2021-562)**Iván Vallés-Ṕerez, Julian Roth, Grzegorz Beringer et al.*7 citations*
475. **[Improving RNN-T ASR Accuracy Using Context Audio ↗](https://doi.org/10.21437/interspeech.2021-542)**Andreas Schwarz, Ilya Sklyar, Simon Wiesler*7 citations*
476. **[Insights on Neural Representations for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1516)**Anna Ollerenshaw, Md Asif Jalal, Thomas Hain*7 citations*
477. **[Integrating Dialog History into End-to-End Spoken Language Understanding Systems ↗](https://doi.org/10.21437/interspeech.2021-1460)**Jatin Ganhotra, Samuel Thomas, Hong-Kwang Jeff Kuo et al.*7 citations*
478. **[Introducing a Central African Primate Vocalisation Dataset for Automated Species Classification ↗](https://doi.org/10.21437/interspeech.2021-154)**Joeri A. Zwerts, Jelle Treep, Casper Kaandorp et al.*7 citations*
479. **[Investigating Feature Selection and Explainability for COVID-19 Diagnostics from Cough Sounds ↗](https://doi.org/10.21437/interspeech.2021-2197)**Flávio R. Ávila, Amir Hossein Poorjam, Deepak Mittal et al.*7 citations*
480. **[L1 Identification from L2 Speech Using Neural Spectrogram Analysis ↗](https://doi.org/10.21437/interspeech.2021-1545)**Calbert Graham*7 citations*
481. **[Log-Likelihood-Ratio Cost Function as Objective Loss for Speaker Verification Systems ↗](https://doi.org/10.21437/interspeech.2021-1085)**Victoria Mingote, Antonio Miguel, Alfonso Ortega et al.*7 citations*
482. **[Normalization Driven Zero-Shot Multi-Speaker Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-441)**Neeraj Kumar, Srishti Goel, Ankur Narang et al.*7 citations*
483. **[On Modeling Glottal Source Information for Phonation Assessment in Parkinson’s Disease ↗](https://doi.org/10.21437/interspeech.2021-1084)**Juan Camilo Vásquez-Correa, Julian Fritsch, Juan Rafael Orozco‐Arroyave et al.*7 citations*
484. **[OpenASR20: An Open Challenge for Automatic Speech Recognition of Conversational Telephone Speech in Low-Resource Languages ↗](https://doi.org/10.21437/interspeech.2021-1930)**Kay Peterson, Audrey N. Tong, Yan H. Yu*7 citations*
485. **[PDF: Polyphone Disambiguation in Chinese by Using FLAT ↗](https://doi.org/10.21437/interspeech.2021-1087)**Haiteng Zhang*7 citations*
486. **[Phoneme Duration Modeling Using Speech Rhythm-Based Speaker Embeddings for Multi-Speaker Speech Synthesis ↗](https://doi.org/10.21437/interspeech.2021-826)**Kenichi Fujita, Atsushi Ando, Yusuke Ijima*7 citations*
487. **[Phoneme Recognition Through Fine Tuning of Phonetic Representations: A Case Study on Luhya Language Varieties ↗](https://doi.org/10.21437/interspeech.2021-1434)**Kathleen Siminyu, Xinjian Li, Antonios Anastasopoulos et al.*7 citations*
488. **[Phonetically Induced Subwords for End-to-End Speech Recognition ↗](https://doi.org/10.21437/interspeech.2021-1787)**Vasileios Papadourakis, Markus Müller, Jing Liu et al.*7 citations*
489. **[Robust End-to-End Speaker Diarization with Conformer and Additive Margin Penalty ↗](https://doi.org/10.21437/interspeech.2021-1377)**Tsun-Yat Leung, Lahiru Samarakoon*7 citations*
490. **[Scene-Agnostic Multi-Microphone Speech Dereverberation ↗](https://doi.org/10.21437/interspeech.2021-889)**Yochai Yemini, Ethan Fetaya, Haggai Maron et al.*7 citations*
491. **[Semantic Transportation Prototypical Network for Few-Shot Intent Detection ↗](https://doi.org/10.21437/interspeech.2021-548)**Weiyuan Xu, Peilin Zhou, Chenyu You et al.*7 citations*
492. **[Simulating Reading Mistakes for Child Speech Transformer-Based Phone Recognition ↗](https://doi.org/10.21437/interspeech.2021-2202)**Lucile Gelin, Thomas Pellegrini, Julien Pinquier et al.*7 citations*
493. **[Speaker Embeddings by Modeling Channel-Wise Correlations ↗](https://doi.org/10.21437/interspeech.2021-1442)**Themos Stafylakis, Johan Rohdin, Lukáš Burget*7 citations*
494. **[Speech Enhancement with Weakly Labelled Data from AudioSet ↗](https://doi.org/10.21437/interspeech.2021-259)**Qiuqiang Kong, Haohe Liu, Xingjian Du et al.*7 citations*
495. **[Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings ↗](https://doi.org/10.21437/interspeech.2021-1704)**Ján Švec, Luboš Šmídl, Josef Psutka et al.*7 citations*
496. **[Take a Breath: Respiratory Sounds Improve Recollection in Synthetic Speech ↗](https://doi.org/10.21437/interspeech.2021-1496)**Mikey Elmers, Raphael Werner, Beeke Muhlack et al.*7 citations*
497. **[The DiCOVA 2021 Challenge — An Encoder-Decoder Approach for COVID-19 Recognition from Coughing Audio ↗](https://doi.org/10.21437/interspeech.2021-811)**Gauri Deshpande, Björn Wolfgang Schuller*7 citations*
498. **[The Impact of Forced-Alignment Errors on Automatic Pronunciation Evaluation ↗](https://doi.org/10.21437/interspeech.2021-1403)**Vikram C. Mathad, Tristan Mahr, Nancy J. Scherer et al.*7 citations*
499. **[Transformer-Based End-to-End Speech Recognition with Residual Gaussian-Based Self-Attention ↗](https://doi.org/10.21437/interspeech.2021-427)**Chengdong Liang, Menglong Xu, Xiao-Lei Zhang*7 citations*
500. **[Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction ↗](https://doi.org/10.21437/interspeech.2021-691)**Hagen Soltau, Mingqiu Wang, Izhak Shafran J et al.*7 citations*

[← prev](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/4/) [1](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/) … [4](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/4/) **5** [6](https://md.research.elamur.ai/free/en/venues/interspeech-usb/2021/papers/page/6/) … [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/6/)

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