Interspeech 2021

999 papers

Speech Emotion Recognition Based on Attention Weight Correction Using Word-Level Confidence Measure

Jennifer Santoso, Takeshi Yamada, Shoji Makino, Kenkichi Ishizuka, Takekatsu Hiramura

A Psychology-Driven Computational Analysis of Political Interviews

Darren Cook, Miri Zilka, Simon Maskell, Laurence Alison

Cross-Modal Learning for Audio-Visual Video Parsing

Jatin Lamba, Abhishek, Jayaprakash Akula, Rishabh Dabral, Preethi Jyothi

Neural Speaker Embeddings for Ultrasound-Based Silent Speech Interfaces

Amin Honarmandi Shandiz, László Tóth, Gábor Gosztolya, Alexandra Markó, Tamás Gábor Csapó

Late Fusion of the Available Lexicon and Raw Waveform-Based Acoustic Modeling for Depression and Dementia Recognition

Esau Villatoro-tello, S. Pavankumar Dubagunta, Julian Fritsch, Gabriela Ramírez-de-la-Rosa, Petr Motlicek

The Impact of Forced-Alignment Errors on Automatic Pronunciation Evaluation

Vikram C. Mathad, Tristan J. Mahr, Nancy Scherer, Kathy Chapman, Katherine C. Hustad

Speech Disorder Classification Using Extended Factorized Hierarchical Variational Auto-Encoders

Jinzi Qi, Hugo Van hamme

Automatic Extraction of Speech Rhythm Descriptors for Speech Intelligibility Assessment in the Context of Head and Neck Cancers

Robin Vaysse, Jérôme Farinas, Corine Astésano, Régine Andre-Obrecht

Automatically Detecting Errors and Disfluencies in Read Speech to Predict Cognitive Impairment in People with Parkinson’s Disease

Amrit Romana, John Bandon, Matthew Perez, Stephanie Gutierrez, Richard Richter

Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation

Paul-Gauthier Noé, Mohammad Mohammadamini, Driss Matrouf, Titouan Parcollet, Andreas Nautsch

Knowledge Distillation from Multi-Modality to Single-Modality for Person Verification

Leying Zhang, Zhengyang Chen, Yanmin Qian

Fair Voice Biometrics: Impact of Demographic Imbalance on Group Fairness in Speaker Recognition

Gianni Fenu, Mirko Marras, Giacomo Medda, Giacomo Meloni

Using Games to Augment Corpora for Language Recognition and Confusability

Christopher Cieri, James Fiumara, Jonathan Wright

Fast Text-Only Domain Adaptation of RNN-Transducer Prediction Network

Janne Pylkkönen, Antti Ukkonen, Juho Kilpikoski, Samu Tamminen, Hannes Heikinheimo

On Sampling-Based Training Criteria for Neural Language Modeling

Yingbo Gao, David Thulke, Alexander Gerstenberger, Khoa Viet Tran, Ralf Schlüter

Text Augmentation for Language Models in High Error Recognition Scenario

Karel Beneš, Lukas Burget

BERT-Based Semantic Model for Rescoring N-Best Speech Recognition List

Dominique Fohr, Irina Illina

Ethical and Technological Challenges of Conversational AI

Pascale Fung

Uncovering the Acoustic Cues of COVID-19 Infection

Sriram Ganapathy

Real-Time Multi-Channel Speech Enhancement Based on Neural Network Masking with Attention Model

Cheng Xue, Weilong Huang, Weiguang Chen, Jinwei Feng

SRIB-LEAP Submission to Far-Field Multi-Channel Speech Enhancement Challenge for Video Conferencing

R.G. Prithvi Raj, Rohit Kumar, M.K. Jayesh, Anurenjan Purushothaman, Sriram Ganapathy

Inplace Gated Convolutional Recurrent Neural Network for Dual-Channel Speech Enhancement

Jinjiang Liu, Xueliang Zhang

Improving Channel Decorrelation for Multi-Channel Target Speech Extraction

Jiangyu Han, Wei Rao, Yannan Wang, Yanhua Long

Real-Time Independent Vector Analysis Using Semi-Supervised Nonnegative Matrix Factorization as a Source Model

Taihui Wang, Feiran Yang, Rui Zhu, Jun Yang

A Partitioned-Block Frequency-Domain Adaptive Kalman Filter for Stereophonic Acoustic Echo Cancellation

Rui Zhu, Feiran Yang, Yuepeng Li, Shidong Shang

A Causal U-Net Based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement

Xinlei Ren, Xu Zhang, Lianwu Chen, Xiguang Zheng, Chen Zhang

Multi-Mode Transformer Transducer with Stochastic Future Context

Kwangyoun Kim, Felix Wu, Prashant Sridhar, Kyu J. Han, Shinji Watanabe

Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition

Niko Moritz, Takaaki Hori, Jonathan Le Roux

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR

Hirofumi Inaguma, Tatsuya Kawahara

Mixture Model Attention: Flexible Streaming and Non-Streaming Automatic Speech Recognition

Kartik Audhkhasi, Tongzhou Chen, Bhuvana Ramabhadran, Pedro J. Moreno

Bridging the Gap Between Streaming and Non-Streaming ASR Systems by Distilling Ensembles of CTC and RNN-T Models

Thibault Doutre, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Olivier Siohan

Reducing Exposure Bias in Training Recurrent Neural Network Transducers

Xiaodong Cui, Brian Kingsbury, George Saon, David Haws, Zoltán Tüske

HMM-Free Encoder Pre-Training for Streaming RNN Transducer

Lu Huang, Jingyu Sun, Yufeng Tang, JunFeng Hou, Jinkun Chen

Improving RNN-T ASR Accuracy Using Context Audio

Andreas Schwarz, Ilya Sklyar, Simon Wiesler

Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture

Takafumi Moriya, Tomohiro Tanaka, Takanori Ashihara, Tsubasa Ochiai, Hiroshi Sato

Streaming Multi-Talker Speech Recognition with Joint Speaker Identification

Liang Lu, Naoyuki Kanda, Jinyu Li, Yifan Gong

An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling

Tara N. Sainath, Yanzhang He, Arun Narayanan, Rami Botros, Ruoming Pang

Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion

Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi

Multiple Softmax Architecture for Streaming Multilingual End-to-End ASR Systems

Vikas Joshi, Amit Das, Eric Sun, Rupesh R. Mehta, Jinyu Li

Super-Human Performance in Online Low-Latency Recognition of Conversational Speech

Thai-Son Nguyen, Sebastian Stüker, Alex Waibel

Investigating the Impact of Spectral and Temporal Degradation on End-to-End Automatic Speech Recognition Performance

Takanori Ashihara, Takafumi Moriya, Makio Kashino

Primacy of Mouth over Eyes: Eye Movement Evidence from Audiovisual Mandarin Lexical Tones and Vowels

Biao Zeng, Rui Wang, Guoxing Yu, Christian Dobel

Towards the Explainability of Multimodal Speech Emotion Recognition

Puneet Kumar, Vishesh Kaushik, Balasubramanian Raman

Reliable Estimates of Interpretable Cue Effects with Active Learning in Psycholinguistic Research

Marieke Einfeldt, Rita Sevastjanova, Katharina Zahner-Ritter, Ekaterina Kazak, Bettina Braun

Human Spoofing Detection Performance on Degraded Speech

Camryn Terblanche, Philip Harrison, Amelia J. Gully

Relationships Between Perceptual Distinctiveness, Articulatory Complexity and Functional Load in Speech Communication

Yuqing Zhang, Zhu Li, Bin Wu, Yanlu Xie, Binghuai Lin

Effects of Aging and Age-Related Hearing Loss on Talker Discrimination

Min Xu, Jing Shao, Lan Wang

VocalTurk: Exploring Feasibility of Crowdsourced Speaker Identification

Susumu Saito, Yuta Ide, Teppei Nakano, Tetsuji Ogawa

SpeechAdjuster: A Tool for Investigating Listener Preferences and Speech Intelligibility

Olympia Simantiraki, Martin Cooke

Exploring the Potential of Lexical Paraphrases for Mitigating Noise-Induced Comprehension Errors

Anupama Chingacham, Vera Demberg, Dietrich Klakow

The Influence of Parallel Processing on Illusory Vowels

Takeshi Kishiyama

Perception of Standard Arabic Synthetic Speech Rate

Yahya Aldholmi, Rawan Aldhafyan, Asma Alqahtani

Protecting Gender and Identity with Disentangled Speech Representations

Dimitrios Stoidis, Andrea Cavallaro

Development of a Psychoacoustic Loss Function for the Deep Neural Network (DNN)-Based Speech Coder

Joon Byun, Seungmin Shin, Youngcheol Park, Jongmo Sung, Seungkwon Beack

A Two-Stage Approach to Speech Bandwidth Extension

Ju Lin, Yun Wang, Kaustubh Kalgaonkar, Gil Keren, Didi Zhang

Voice Privacy Through x-Vector and CycleGAN-Based Anonymization

Gauri P. Prajapati, Dipesh K. Singh, Preet P. Amin, Hemant A. Patil

Improving the Expressiveness of Neural Vocoding with Non-Affine Normalizing Flows

Adam Gabryś, Yunlong Jiao, Viacheslav Klimkov, Daniel Korzekwa, Roberto Barra-Chicote

Effects of Prosodic Variations on Accidental Triggers of a Commercial Voice Assistant

Ingo Siegert

Multi-Channel Opus Compression for Far-Field Automatic Speech Recognition with a Fixed Bitrate Budget

Lukas Drude, Jahn Heymann, Andreas Schwarz, Jean-Marc Valin

Coded Speech Enhancement Using Neural Network-Based Vector-Quantized Residual Features

Youngju Cheon, Soojoong Hwang, Sangwook Han, Inseon Jang, Jong Won Shin

Data Quality as Predictor of Voice Anti-Spoofing Generalization

Bhusan Chettri, Rosa Gonzalez Hautamäki, Md. Sahidullah, Tomi Kinnunen

Half-Truth: A Partially Fake Audio Detection Dataset

Jiangyan Yi, Ye Bai, Jianhua Tao, Haoxin Ma, Zhengkun Tian

WSRGlow: A Glow-Based Waveform Generative Model for Audio Super-Resolution

Kexun Zhang, Yi Ren, Changliang Xu, Zhou Zhao

X-net: A Joint Scale Down and Scale Up Method for Voice Call

Liang Wen, Lizhong Wang, Xue Wen, Yuxing Zheng, Youngo Park

QISTA-Net-Audio: Audio Super-Resolution via Non-Convex ℓ_q-Norm Minimization

Gang-Xuan Lin, Shih-Wei Hu, Yen-Ju Lu, Yu Tsao, Chun-Shien Lu

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling

Junhyeok Lee, Seungu Han

Speech2Video: Cross-Modal Distillation for Speech to Video Generation

Shijing Si, Jianzong Wang, Xiaoyang Qu, Ning Cheng, Wenqi Wei

Investigating Contributions of Speech and Facial Landmarks for Talking Head Generation

Ege Kesim, Engin Erzin

Incorporating Cross-Speaker Style Transfer for Multi-Language Text-to-Speech

Zengqiang Shang, Zhihua Huang, Haozhe Zhang, Pengyuan Zhang, Yonghong Yan

Cross-Lingual Speaker Adaptation Using Domain Adaptation and Speaker Consistency Loss for Text-To-Speech Synthesis

Detai Xin, Yuki Saito, Shinnosuke Takamichi, Tomoki Koriyama, Hiroshi Saruwatari

EfficientSing: A Chinese Singing Voice Synthesis System Using Duration-Free Acoustic Model and HiFi-GAN Vocoder

Zhengchen Liu, Chenfeng Miao, Qingying Zhu, Minchuan Chen, Jun Ma

Cross-Lingual Voice Conversion with Disentangled Universal Linguistic Representations

Zhenchuan Yang, Weibin Zhang, Yufei Liu, Xiaofen Xing

Improve Cross-Lingual Text-To-Speech Synthesis on Monolingual Corpora with Pitch Contour Information

Haoyue Zhan, Haitong Zhang, Wenjie Ou, Yue Lin

Cross-Lingual Low Resource Speaker Adaptation Using Phonological Features

Georgia Maniati, Nikolaos Ellinas, Konstantinos Markopoulos, Georgios Vamvoukakis, June Sig Sung

N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement

Gyeong-Hoon Lee, Tae-Woo Kim, Hanbin Bae, Min-Ji Lee, Young-Ik Kim

AVLnet: Learning Audio-Visual Language Representations from Instructional Videos

Andrew Rouditchenko, Angie Boggust, David Harwath, Brian Chen, Dhiraj Joshi

Zero-Shot Federated Learning with New Classes for Audio Classification

Gautham Krishna Gudur, Satheesh Kumar Perepu

The Zero Resource Speech Challenge 2021: Spoken Language Modelling

Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel

Identifying Indicators of Vulnerability from Short Speech Segments Using Acoustic and Textual Features

Xia Cui, Amila Gamage, Terry Hanley, Tingting Mu

Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021

Takashi Maekaku, Xuankai Chang, Yuya Fujita, Li-Wei Chen, Shinji Watanabe

Unsupervised Neural-Based Graph Clustering for Variable-Length Speech Representation Discovery of Zero-Resource Languages

Shun Takahashi, Sakriani Sakti, Satoshi Nakamura

Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing

Benjamin Van Niekerk, Leanne Nortje, Matthew Baas, Herman Kamper

Multilingual Transfer of Acoustic Word Embeddings Improves When Training on Languages Related to the Target Zero-Resource Language

Christiaan Jacobs, Herman Kamper

Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation Learning

Dongwei Jiang, Wubo Li, Miao Cao, Wei Zou, Xiangang Li

Towards Unsupervised Phone and Word Segmentation Using Self-Supervised Vector-Quantized Neural Networks

Herman Kamper, Benjamin Van Niekerk

Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation

Siyuan Feng, Piotr Żelasko, Laureano Moro-Velazquez, Odette Scharenborg

Low Resource ASR: The Surprising Effectiveness of High Resource Transliteration

Shreya Khare, Ashish Mittal, Anuj Diwan, Sunita Sarawagi, Preethi Jyothi

Excitation Source Feature Based Dialect Identification in Ao — A Low Resource Language

Moakala Tzudir, Shikha Baghel, Priyankoo Sarmah, S.R. Mahadeva Prasanna

E2E-Based Multi-Task Learning Approach to Joint Speech and Accent Recognition

Jicheng Zhang, Yizhou Peng, Van Tung Pham, Haihua Xu, Hao Huang

Self-Supervised Phonotactic Representations for Language Identification

G. Ramesh, C. Shiva Kumar, K. Sri Rama Murty

Exploring wav2vec 2.0 on Speaker Verification and Language Identification

Zhiyun Fan, Meng Li, Shiyu Zhou, Bo Xu

Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-Supervised Learning

Keqi Deng, Songjun Cao, Long Ma

A Weight Moving Average Based Alternate Decoupled Learning Algorithm for Long-Tailed Language Identification

Hui Wang, Lin Liu, Yan Song, Lei Fang, Ian McLoughlin

Modeling and Training Strategies for Language Recognition Systems

Raphaël Duroselle, Md. Sahidullah, Denis Jouvet, Irina Illina

End-to-End Language Diarization for Bilingual Code-Switching Speech

Hexin Liu, Leibny Paola García Perera, Xinyi Zhang, Justin Dauwels, Andy W.H. Khong

Real-Time Speaker Counting in a Cocktail Party Scenario Using Attention-Guided Convolutional Neural Network

Midia Yousefi, John H.L. Hansen

Time Delay Estimation for Speaker Localization Using CNN-Based Parametrized GCC-PHAT Features

Daniele Salvati, Carlo Drioli, Gian Luca Foresti

Using X-Vectors for Speech Activity Detection in Broadcast Streams

Lukas Mateju, Frantisek Kynych, Petr Cerva, Jindrich Zdansky, Jiri Malek

Universal Speaker Extraction in the Presence and Absence of Target Speakers for Speech of One and Two Talkers

Marvin Borsdorf, Chenglin Xu, Haizhou Li, Tanja Schultz

Auxiliary Loss Function for Target Speech Extraction and Recognition with Weak Supervision Based on Speaker Characteristics

Kateřina Žmolíková, Marc Delcroix, Desh Raj, Shinji Watanabe, Jan Černocký