Interspeech 2020

1,035 papers

Speech Emotion Recognition with Discriminative Feature Learning

Huan Zhou, Kai Liu

Adaptive Domain-Aware Representation Learning for Speech Emotion Recognition

Weiquan Fan, Xiangmin Xu, Xiaofen Xing, Dongyan Huang

Removing Bias with Residual Mixture of Multi-View Attention for Speech Emotion Recognition

Md. Asif Jalal, Rosanna Milner, Thomas Hain, Roger K. Moore

Learning Utterance-Level Representations with Label Smoothing for Speech Emotion Recognition

Jian Huang, Jianhua Tao, Bin Liu, Zheng Lian

Phase-Aware Music Super-Resolution Using Generative Adversarial Networks

Shichao Hu, Bin Zhang, Beici Liang, Ethan Zhao, Simon Lui

Multi-Task Learning for End-to-End Noise-Robust Bandwidth Extension

Nana Hou, Chenglin Xu, Joey Tianyi Zhou, Eng Siong Chng, Haizhou Li

Speaker and Phoneme-Aware Speech Bandwidth Extension with Residual Dual-Path Network

Nana Hou, Chenglin Xu, Van Tung Pham, Joey Tianyi Zhou, Eng Siong Chng

Intelligibility Enhancement Based on Speech Waveform Modification Using Hearing Impairment

Shu Hikosaka, Shogo Seki, Tomoki Hayashi, Kazuhiro Kobayashi, Kazuya Takeda

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

Igor Fedorov, Marko Stamenovic, Carl Jensen, Li-Chia Yang, Ari Mandell

A Cross-Channel Attention-Based Wave-U-Net for Multi-Channel Speech Enhancement

Minh Tri Ho, Jinyoung Lee, Bong-Ki Lee, Dong Hoon Yi, Hong-Goo Kang

Spatial Covariance Matrix Estimation for Reverberant Speech with Application to Speech Enhancement

Ran Weisman, Vladimir Tourbabin, Paul Calamia, Boaz Rafaely

Semi-Supervised Self-Produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-Conducted Signals Using Variational Autoencoder

Shogo Seki, Moe Takada, Tomoki Toda

Adversarial Dictionary Learning for Monaural Speech Enhancement

Yunyun Ji, Longting Xu, Wei-Ping Zhu

Exploiting Conic Affinity Measures to Design Speech Enhancement Systems Operating in Unseen Noise Conditions

Pavlos Papadopoulos, Shrikanth Narayanan

MultiSpeech: Multi-Speaker Text to Speech with Transformer

Mingjian Chen, Xu Tan, Yi Ren, Jin Xu, Hao Sun

Testing the Limits of Representation Mixing for Pronunciation Correction in End-to-End Speech Synthesis

Jason Fong, Jason Taylor, Simon King

Attention Forcing for Speech Synthesis

Qingyun Dou, Joshua Efiong, Mark J.F. Gales

End-to-End Text-to-Speech Synthesis with Unaligned Multiple Language Units Based on Attention

Masashi Aso, Shinnosuke Takamichi, Hiroshi Saruwatari

JDI-T: Jointly Trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment

Dan Lim, Won Jang, Gyeonghwan O, Heayoung Park, Bongwan Kim

MoBoAligner: A Neural Alignment Model for Non-Autoregressive TTS with Monotonic Boundary Search

Naihan Li, Shujie LIU, Yanqing Liu, Sheng Zhao, Ming Liu

Naturalness Enhancement with Linguistic Information in End-to-End TTS Using Unsupervised Parallel Encoding

Alex Peiró-Lilja, Mireia Farrús

Bi-Level Speaker Supervision for One-Shot Speech Synthesis

Tao Wang, Jianhua Tao, Ruibo Fu, Jiangyan Yi, Zhengqi Wen

Non-Autoregressive End-to-End TTS with Coarse-to-Fine Decoding

Tao Wang, Xuefei Liu, Jianhua Tao, Jiangyan Yi, Ruibo Fu

Can Speaker Augmentation Improve Multi-Speaker End-to-End TTS?

Erica Cooper, Cheng-I Lai, Yusuke Yasuda, Junichi Yamagishi

From Speaker Verification to Multispeaker Speech Synthesis, Deep Transfer with Feedback Constraint

Zexin Cai, Chuxiong Zhang, Ming Li

Attention Wave-U-Net for Acoustic Echo Cancellation

Jung-Hee Kim, Joon-Hyuk Chang

Improving Partition-Block-Based Acoustic Echo Canceler in Under-Modeling Scenarios

Wenzhi Fan, Jing LU

Nonlinear Residual Echo Suppression Based on Multi-Stream Conv-TasNet

Hongsheng Chen, Teng Xiang, Kai Chen, Jing LU

Independent Echo Path Modeling for Stereophonic Acoustic Echo Cancellation

Yi Gao, Ian Liu, J. Zheng, Cheng Luo, Bin Li

Nonlinear Residual Echo Suppression Using a Recurrent Neural Network

Lukas Pfeifenberger, Franz Pernkopf

Generative Adversarial Network Based Acoustic Echo Cancellation

Yi Zhang, Chengyun Deng, Shiqian Ma, Yongtao Sha, Hui Song

A Robust and Cascaded Acoustic Echo Cancellation Based on Deep Learning

Chenggang Zhang, Xueliang Zhang

SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation Using Optimally Smoothed Spectral Mapping

Vinay Kothapally, Wei Xia, Shahram Ghorbani, John H.L. Hansen, Wei Xue

Virtual Acoustic Channel Expansion Based on Neural Networks for Weighted Prediction Error-Based Speech Dereverberation

Joon-Young Yang, Joon-Hyuk Chang

A Semi-Blind Source Separation Approach for Speech Dereverberation

Ziteng Wang, Yueyue Na, Zhang Liu, Yun Li, Biao Tian

Datasets and Benchmarks for Task-Oriented Log Dialogue Ranking Task

Xinnuo Xu, Yizhe Zhang, Lars Liden, Sungjin Lee

Discriminative Transfer Learning for Optimizing ASR and Semantic Labeling in Task-Oriented Spoken Dialog

Yao Qian, Yu Shi, Michael Zeng

End-to-End Speech-to-Dialog-Act Recognition

Viet-Trung Dang, Tianyu Zhao, Sei Ueno, Hirofumi Inaguma, Tatsuya Kawahara

Task-Oriented Dialog Generation with Enhanced Entity Representation

Zhenhao He, Jiachun Wang, Jian Chen

End-to-End Task-Oriented Dialog System Through Template Slot Value Generation

Teakgyu Hong, Oh-Woog Kwon, Young-Kil Kim

Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption

Hongyin Luo, Shang-Wen Li, James Glass

Conditional Response Augmentation for Dialogue Using Knowledge Distillation

Myeongho Jeong, Seungtaek Choi, Hojae Han, Kyungho Kim, Seung-won Hwang

Stochastic Curiosity Exploration for Dialogue Systems

Jen-Tzung Chien, Po-Chien Hsu

Automatic Estimation of Pathological Voice Quality Based on Recurrent Neural Network Using Amplitude and Phase Spectrogram

Shunsuke Hidaka, Yogaku Lee, Kohei Wakamiya, Takashi Nakagawa, Tokihiko Kaburagi

Domain Adversarial Neural Networks for Dysarthric Speech Recognition

Dominika Woszczyk, Stavros Petridis, David Millard

ASR-Based Evaluation and Feedback for Individualized Reading Practice

Yu Bai, Ferdy Hubers, Catia Cucchiarini, Helmer Strik

Shadowability Annotation with Fine Granularity on L2 Utterances and its Improvement with Native Listeners’ Script-Shadowing

Zhenchao Lin, Ryo Takashima, Daisuke Saito, Nobuaki Minematsu, Noriko Nakanishi

Ensemble Approaches for Uncertainty in Spoken Language Assessment

Xixin Wu, Kate M. Knill, Mark J.F. Gales, Andrey Malinin

Universal Adversarial Attacks on Spoken Language Assessment Systems

Vyas Raina, Mark J.F. Gales, Kate M. Knill

Targeted Content Feedback in Spoken Language Learning and Assessment

Xinhao Wang, Klaus Zechner, Christopher Hamill

Mixtures of Deep Neural Experts for Automated Speech Scoring

Sara Papi, Edmondo Trentin, Roberto Gretter, Marco Matassoni, Daniele Falavigna

Spoken Language ‘Grammatical Error Correction’

Yiting Lu, Mark J.F. Gales, Yu Wang

Length- and Noise-Aware Training Techniques for Short-Utterance Speaker Recognition

Wenda Chen, Jonathan Huang, Tobias Bocklet

ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification

Brecht Desplanques, Jenthe Thienpondt, Kris Demuynck

Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning

Jiawen Kang, Ruiqi Liu, Lantian Li, Yunqi Cai, Dong Wang

Angular Margin Centroid Loss for Text-Independent Speaker Recognition

Yuheng Wei, Junzhao Du, Hui LIU

Supervised Domain Adaptation for Text-Independent Speaker Verification Using Limited Data

Seyyed Saeed Sarfjoo, Srikanth Madikeri, Petr Motlicek, Sébastien Marcel

Training Speaker Enrollment Models by Network Optimization

Victoria Mingote, Antonio Miguel, Alfonso Ortega, Eduardo Lleida

On Parameter Adaptation in Softmax-Based Cross-Entropy Loss for Improved Convergence Speed and Accuracy in DNN-Based Speaker Recognition

Magdalena Rybicka, Konrad Kowalczyk

Dynamic Margin Softmax Loss for Speaker Verification

Dao Zhou, Longbiao Wang, Kong Aik Lee, Yibo Wu, Meng Liu

Automatic Speech Recognition for ILSE-Interviews: Longitudinal Conversational Speech Recordings Covering Aging and Cognitive Decline

Ayimunishagu Abulimiti, Jochen Weiner, Tanja Schultz

A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning

Sameer Khurana, Antoine Laurent, Wei-Ning Hsu, Jan Chorowski, Adrian Lancucki

Understanding Self-Attention of Self-Supervised Audio Transformers

Shu-wen Yang, Andy T. Liu, Hung-yi Lee

Defense for Black-Box Attacks on Anti-Spoofing Models by Self-Supervised Learning

Haibin Wu, Andy T. Liu, Hung-yi Lee

Sequence-Level Self-Learning with Multiple Hypotheses

Kenichi Kumatani, Dimitrios Dimitriadis, Yashesh Gaur, Robert Gmyr, Sefik Emre Eskimez

Large Scale Weakly and Semi-Supervised Learning for Low-Resource Video ASR

Kritika Singh, Vimal Manohar, Alex Xiao, Sergey Edunov, Ross Girshick

Speech-XLNet: Unsupervised Acoustic Model Pretraining for Self-Attention Networks

Xingchen Song, Guangsen Wang, Yiheng Huang, Zhiyong Wu, Dan Su

Vector-Quantized Autoregressive Predictive Coding

Yu-An Chung, Hao Tang, James Glass

Jointly Fine-Tuning “BERT-Like” Self Supervised Models to Improve Multimodal Speech Emotion Recognition

Shamane Siriwardhana, Andrew Reis, Rivindu Weerasekera, Suranga Nanayakkara

Links Between Production and Perception of Glottalisation in Individual Australian English Speaker/Listeners

Joshua Penney, Felicity Cox, Anita Szakay

CSL-EMG_Array: An Open Access Corpus for EMG-to-Speech Conversion

Lorenz Diener, Mehrdad Roustay Vishkasougheh, Tanja Schultz

Independent and Automatic Evaluation of Speaker-Independent Acoustic-to-Articulatory Reconstruction

Maud Parrot, Juliette MILLET, Ewan Dunbar

Quantification of Transducer Misalignment in Ultrasound Tongue Imaging

Tamás Gábor Csapó, Kele Xu

Using Silence MR Image to Synthesise Dynamic MRI Vocal Tract Data of CV

Ioannis K. Douros, Ajinkya Kulkarni, Chrysanthi Dourou, Yu Xie, Jacques Felblinger

Acoustic-to-Articulatory Inversion with Deep Autoregressive Articulatory-WaveNet

Narjes Bozorg, Michael T. Johnson

Speaker Dependent Acoustic-to-Articulatory Inversion Using Real-Time MRI of the Vocal Tract

Tamás Gábor Csapó

Discovering Articulatory Speech Targets from Synthesized Random Babble

Heikki Rasilo, Yannick Jadoul

Analyzing Read Aloud Speech by Primary School Pupils: Insights for Research and Development

S. Limonard, Catia Cucchiarini, R.W.N.M. van Hout, Helmer Strik

That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages

Piotr Żelasko, Laureano Moro-Velazquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak

Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation

Felix Kreuk, Joseph Keshet, Yossi Adi

MLNET: An Adaptive Multiple Receptive-Field Attention Neural Network for Voice Activity Detection

Zhenpeng Zheng, Jianzong Wang, Ning Cheng, Jian Luo, Jing Xiao

VOP Detection in Variable Speech Rate Condition

Ayush Agarwal, Jagabandhu Mishra, S.R. Mahadeva Prasanna

End-to-End Domain-Adversarial Voice Activity Detection

Marvin Lavechin, Marie-Philippe Gill, Ruben Bousbib, Hervé Bredin, Leibny Paola García-Perera

A Noise Robust Technique for Detecting Vowels in Speech Signals

Avinash Kumar, S. Shahnawazuddin, Waquar Ahmad

Polishing the Classical Likelihood Ratio Test by Supervised Learning for Voice Activity Detection

Tianjiao Xu, Hui Zhang, Xueliang Zhang

Dual Attention in Time and Frequency Domain for Voice Activity Detection

Joohyung Lee, Youngmoon Jung, Hoirin Kim

Voice Activity Detection in the Wild via Weakly Supervised Sound Event Detection

Yefei Chen, Heinrich Dinkel, Mengyue Wu, Kai Yu

Insertion-Based Modeling for End-to-End Automatic Speech Recognition

Yuya Fujita, Shinji Watanabe, Motoi Omachi, Xuankai Chang

Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict

Yosuke Higuchi, Shinji Watanabe, Nanxin Chen, Tetsuji Ogawa, Tetsunori Kobayashi

Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model

Da-Rong Liu, Chunxi Liu, Frank Zhang, Gabriel Synnaeve, Yatharth Saraf

Investigation of Large-Margin Softmax in Neural Language Modeling

Jingjing Huo, Yingbo Gao, Weiyue Wang, Ralf Schlüter, Hermann Ney

Stochastic Convolutional Recurrent Networks for Language Modeling

Jen-Tzung Chien, Yu-Min Huang

Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

Hayato Futami, Hirofumi Inaguma, Sei Ueno, Masato Mimura, Shinsuke Sakai

Finnish ASR with Deep Transformer Models

Abhilash Jain, Aku Rouhe, Stig-Arne Grönroos, Mikko Kurimo

Neural Language Modeling with Implicit Cache Pointers

Ke Li, Daniel Povey, Sanjeev Khudanpur

Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection

Danni Liu, Gerasimos Spanakis, Jan Niehues

Emitting Word Timings with End-to-End Models

Tara N. Sainath, Ruoming Pang, David Rybach, Basi García, Trevor Strohman

ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context

Wei Han, Zhengdong Zhang, Yu Zhang, Jiahui Yu, Chung-Cheng Chiu

Early Stage LM Integration Using Local and Global Log-Linear Combination

Wilfried Michel, Ralf Schlüter, Hermann Ney

Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition

Egor Lakomkin, Jahn Heymann, Ilya Sklyar, Simon Wiesler