Interspeech 2022

1,123 papers

User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning

Tiantian Feng, Raghuveer Peri, Shrikanth Narayanan

Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling

Tiantian Feng, Shrikanth Narayanan

Chunking Defense for Adversarial Attacks on ASR

Yiwen Shao, Jesus Villalba, Sonal Joshi, Saurabh Kataria, Sanjeev Khudanpur

Membership Inference Attacks Against Self-supervised Speech Models

Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee

Defense against Adversarial Attacks on Hybrid Speech Recognition System using Adversarial Fine-tuning with Denoiser

Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Żelasko, Jesus Villalba

An Attention-Based Method for Guiding Attribute-Aligned Speech Representation Learning

Yu-Lin Huang, Bo-Hao Su, Y.-W. Peter Hong, Chi-Chun Lee

Enhancing Speech Privacy with Slicing

Mohamed Maouche, Brij Mohan Lal Srivastava, Nathalie Vauquier, Aurélien Bellet, Marc Tommasi

Acoustic-to-articulatory Speech Inversion with Multi-task Learning

Yashish M. Siriwardena, Ganesh Sivaraman, Carol Espy-Wilson

A study on constraining Connectionist Temporal Classification for temporal audio alignment

Yann Teytaut, Baptiste Bouvier, Axel Roebel

Overlapped speech and gender detection with WavLM pre-trained features

Martin Lebourdais, Marie Tahon, Antoine Laurent, Sylvain Meignier

An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks

Kai-Wei Chang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee

Autoregressive Co-Training for Learning Discrete Speech Representation

Sung-Lin Yeh, Hao Tang

E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR

W. Ronny Huang, Shuo-Yiin Chang, David Rybach, Tara Sainath, Rohit Prabhavalkar

Where's the uh, hesitation? The interplay between filled pause location, speech rate and fundamental frequency in perception of confidence

Ambika Kirkland, Harm Lameris, Eva Szekely, Joakim Gustafson

Production Strategies of Vocal Attitudes

Léane Salais, Pablo Arias, Clément Le Moine, Victor Rosi, Yann Teytaut

Representing 'how you say' with 'what you say': English corpus of focused speech and text reflecting corresponding implications

Naoaki Suzuki, Satoshi Nakamura

Discriminative Adversarial Learning for Speaker Independent Emotion Recognition

Chamara Kasun, Chung Soo Ahn, Jagath Rajapakse, Zhiping Lin, Guang-Bin Huang

Cross-Cultural Comparison of Gradient Emotion Perception: Human vs. Alexa TTS Voices

Iona Gessinger, Michelle Cohn, Georgia Zellou, Bernd Möbius

Better Intermediates Improve CTC Inference

Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee, Lukas Lee, Shinji Watanabe

RNN-T lattice enhancement by grafting of pruned paths

Mirek Novak, Pavlos Papadopoulos

Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model

Martin Kocour, Kateřina Žmolíková, Lucas Ondel, Jan Švec, Marc Delcroix

Wav2Vec-Aug: Improved self-supervised training with limited data

Anuroop Sriram, Michael Auli, Alexei Baevski

K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables

Jounghee Kim, Pilsung Kang

Improving Deliberation by Text-Only and Semi-Supervised Training

Ke Hu, Tara Sainath, Yanzhang He, Rohit Prabhavalkar, Trevor Strohman

Self supervised learning for robust voice cloning

Konstantinos Klapsas, Nikolaos Ellinas, Karolos Nikitaras, Georgios Vamvoukakis, Panagiotis Kakoulidis

Investigation into Target Speaking Rate Adaptation for Voice Conversion

Michael Kuhlmann, Fritz Seebauer, Janek Ebbers, Petra Wagner, Reinhold Haeb-Umbach

Speaker Anonymization with Phonetic Intermediate Representations

Sarina Meyer, Florian Lux, Pavel Denisov, Julia Koch, Pascal Tilli

Zero-Shot Foreign Accent Conversion without a Native Reference

Waris Quamer, Anurag Das, John Levis, Evgeny Chukharev-Hudilainen, Ricardo Gutierrez-Osuna

An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion

Zijiang Yang, Xin Jing, Andreas Triantafyllopoulos, Meishu Song, Ilhan Aslan

An Evaluation of Three-Stage Voice Conversion Framework for Noisy and Reverberant Conditions

Yeonjong Choi, Chao Xie, Tomoki Toda

Plugging a neural phoneme recognizer into a simple language model: a workflow for low-resource setting

Séverine Guillaume, Guillaume Wisniewski, Benjamin Galliot, Minh-Châu Nguyên, Maxime Fily

DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children’s ASR

Ruchao Fan, Abeer Alwan

OpenASR21: The Second Open Challenge for Automatic Speech Recognition of Low-Resource Languages

Kay Peterson, Audrey Tong, Yan Yu

Combining Simple but Novel Data Augmentation Methods for Improving Conformer ASR

Ronit Damania, Christopher Homan, Emily Prud'hommeaux

ASR2K: Speech Recognition for Around 2000 Languages without Audio

Xinjian Li, Florian Metze, David R. Mortensen, Alan W Black, Shinji Watanabe

Using cross-model learnings for the Gram Vaani ASR Challenge 2022

Tanvina Patel, Odette Scharenborg

Comparison of Unsupervised Learning and Supervised Learning with Noisy Labels for Low-Resource Speech Recognition

Yanick Schraner, Christian Scheller, Michel Plüss, Lukas Neukom, Manfred Vogel

Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR

Han Zhu, Li Wang, Gaofeng Cheng, Jindong Wang, Pengyuan Zhang

Cross-dialect lexicon optimisation for an endangered language ASR system: the case of Irish

Liam Lonergan, Mengjie Qian, Neasa Ní Chiaráin, Christer Gobl, Ailbhe Ni Chasaide

External Text Based Data Augmentation for Low-Resource Speech Recognition in the Constrained Condition of OpenASR21 Challenge

Guolong Zhong, Hongyu Song, Ruoyu Wang, Lei Sun, Diyuan Liu

The THUEE System Description for the IARPA OpenASR21 Challenge

Jing Zhao, Haoyu Wang, Jinpeng Li, Shuzhou Chai, Guanbo Wang

Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion

Muhammad Umar Farooq, Darshan Adiga Haniya Narayana, Thomas Hain

Incremental Layer-Wise Self-Supervised Learning for Efficient Unsupervised Speech Domain Adaptation On Device

Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra

A study of production error analysis for Mandarin-speaking Children with Hearing Impairment

Jingwen Cheng, Yuchen Yan, Yingming Gao, Xiaoli Feng, Yannan Wang

A user-friendly headset for radar-based silent speech recognition

Pouriya Amini Digehsara, João Vítor Possamai de Menezes, Christoph Wagner, Michael Bärhold, Petr Schaffer

Revisiting visuo-spatial processing in individuals with congenital amusia

Zixia Fan, Jing Shao, Weigong Pan, Lan Wang

Conformer Based Elderly Speech Recognition System for Alzheimer’s Disease Detection

Tianzi Wang, Jiajun Deng, Mengzhe Geng, Zi Ye, Shoukang Hu

Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech

Kaitao Song, Teng Wan, Bixia Wang, Huiqiang Jiang, Luna Qiu

Disentangled Latent Speech Representation for Automatic Pathological Intelligibility Assessment

Tobias Weise, Philipp Klumpp, Andreas Maier, Elmar Nöth, Björn Heismann

Local Context-aware Self-attention for Continuous Sign Language Recognition

Ronglai Zuo, Brian Mak

Graph-based Multi-View Fusion and Local Adaptation: Mitigating Within-Household Confusability for Speaker Identification

Long Chen, Yixiong Meng, Venkatesh Ravichandran, Andreas Stolcke

Adversarial Reweighting for Speaker Verification Fairness

Minho Jin, Chelsea Ju, Zeya Chen, Yi Chieh Liu, Jasha Droppo

Multi-Path GMM-MobileNet Based on Attack Algorithms and Codecs for Synthetic Speech and Deepfake Detection

Yan Wen, Zhenchun Lei, Yingen Yang, Changhong Liu, Minglei Ma

Acoustic Feature Shuffling Network for Text-independent Speaker Verification

Jin Li, Xin Fang, Fan Chu, Tian Gao, Yan Song

Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT

Bowen Shi, Abdelrahman Mohamed, Wei-Ning Hsu

Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction

Bing Han, Zhengyang Chen, Yanmin Qian

A Novel Phoneme-based Modeling for Text-independent Speaker Identification

Xin Wang, Chuan Xie, Qiang Wu, Huayi Zhan, Ying Wu

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network

Haodong Zhao, Wei Du, Junjie Guo, Gongshen Liu

A Deep One-Class Learning Method for Replay Attack Detection

Yijie Lou, Shiliang Pu, Jianfeng Zhou, Xin Qi, Qinbo Dong

Training speaker recognition systems with limited data

Nik Vaessen, David Van Leeuwen

Intra-speaker phonetic variation in read speech: comparison with inter-speaker variability in a controlled population

Nicolas Audibert, Cécile Fougeron

Discriminative Feature Representation Based on Cascaded Attention Network with Adversarial Joint Loss for Speech Emotion Recognition

Yang Liu, Haoqin Sun, Wenbo Guan, Yuqi Xia, Zhen Zhao

SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning

Zuheng Kang, Junqing Peng, Jianzong Wang, Jing Xiao

Interactive Co-Learning with Cross-Modal Transformer for Audio-Visual Emotion Recognition

Akihiko Takashima, Ryo Masumura, Atsushi Ando, Yoshihiro Yamazaki, Mihiro Uchida

Complex Paralinguistic Analysis of Speech: Predicting Gender, Emotions and Deception in a Hierarchical Framework

Alena Velichko, Maxim Markitantov, Heysem Kaya, Alexey Karpov

CTA-RNN: Channel and Temporal-wise Attention RNN leveraging Pre-trained ASR Embeddings for Speech Emotion Recognition

Chengxin Chen, Pengyuan Zhang

Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition

Zihan Zhao, Yanfeng Wang, Yu Wang

Multiple Enhancements to LSTM for Learning Emotion-Salient Features in Speech Emotion Recognition

Desheng Hu, Xinhui Hu, Xinkang Xu

Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation

Vikramjit Mitra, Hsiang-Yun Sherry Chien, Vasudha Kowtha, Joseph Yitan Cheng, Erdrin Azemi

Speech Emotion Recognition via Generation using an Attention-based Variational Recurrent Neural Network

Murchana Baruah, Bonny Banerjee

A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition

Ying Hu, Yuwu Tang, Hao Huang, Liang He

Performance Improvement of Speech Emotion Recognition by Neutral Speech Detection Using Autoencoder and Intermediate Representation

Jennifer Santoso, Takeshi Yamada, Kenkichi Ishizuka, Taiichi Hashimoto, Shoji Makino

Coupled Discriminant Subspace Alignment for Cross-database Speech Emotion Recognition

Shaokai Li, Peng Song, Keke Zhao, Wenjing Zhang, Wenming Zheng

Vocal-Tract Area Functions with Articulatory Reality for Tract Opening

Zhao Zhang, Ju Zhang, Jianguo Wei, Kiyoshi Honda, Tatsuya Kitamura

Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition

Jiachen Lian, Alan W Black, Louis Goldstein, Gopala Krishna Anumanchipalli

Acoustic To Articulatory Speech Inversion Using Multi-Resolution Spectro-Temporal Representations Of Speech Signals

Rahil Parikh, Nadee Seneviratne, Ganesh Sivaraman, Shihab Shamma, Carol Espy-Wilson

An investigation of regression-based prediction of the femininity or masculinity in speech of transgender people

Leon Liebig, Christoph Wagner, Alexander Mainka, Peter Birkholz

Isochronous is beautiful? Syllabic event detection in a neuro-inspired oscillatory model is facilitated by isochrony in speech

Mamady NABE, Julien Diard, Jean-Luc Schwartz

Radio2Speech: High Quality Speech Recovery from Radio Frequency Signals

Running Zhao, Jiangtao Yu, Tingle Li, Hang Zhao, Edith C. H. Ngai

Unsupervised Inference of Physiologically Meaningful Articulatory Trajectories with VocalTractLab

Yifan Sun, Qinlong Huang, Xihong Wu

Unsupervised Acoustic-to-Articulatory Inversion with Variable Vocal Tract Anatomy

Yifan Sun, Qinlong Huang, Xihong Wu

Investigation on the Band Importance of Phase-aware Speech Enhancement

Zhuohuang Zhang, Donald Williamson, Yi Shen

Unsupervised Word Segmentation using K Nearest Neighbors

Tzeviya Fuchs, Yedid Hoshen, Yossi Keshet

Streaming Automatic Speech Recognition with Re-blocking Processing Based on Integrated Voice Activity Detection

Yui Sudo, Shakeel Muhammad, Kazuhiro Nakadai, Jiatong Shi, Shinji Watanabe

Microphone Array Channel Combination Algorithms for Overlapped Speech Detection

Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas

Multilingual and Multimodal Abuse Detection

Rini Sharon, Heet Shah, Debdoot Mukherjee, Vikram Gupta

Unsupervised Voice Activity Detection by Modeling Source and System Information using Zero Frequency Filtering

Eklavya Sarkar, RaviShankar Prasad, Mathew Magimai Doss

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

Byeonggeun Kim, Seunghan Yang, Inseop Chung, Simyung Chang

SiDi KWS: A Large-Scale Multilingual Dataset for Keyword Spotting

Michel Cardoso Meneses, Rafael Bérgamo Holanda, Luis Vasconcelos Peres, Gabriela Dantas Rocha

DDKtor: Automatic Diadochokinetic Speech Analysis

Yael Segal, Kasia Hitczenko, Matt Goldrick, Adam Buchwald, Angela Roberts

Overlapped Speech Detection in Broadcast Streams Using X-vectors

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

Text aware Emotional Text-to-speech with BERT

Arijit Mukherjee, Shubham Bansal, Sandeepkumar Satpal, Rupesh Mehta

Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems

Hyun-Wook Yoon, Ohsung Kwon, Hoyeon Lee, Ryuichi Yamamoto, Eunwoo Song

Daft-Exprt: Cross-Speaker Prosody Transfer on Any Text for Expressive Speech Synthesis

Julian Zaïdi, Hugo Seuté, Benjamin Van Niekerk, Marc-André Carbonneau

Cross-lingual Style Transfer with Conditional Prior VAE and Style Loss

Dino Rattcliffe, You Wang, Alex Mansbridge, Penny Karanasou, Alexis Moinet

Analysis of expressivity transfer in non-autoregressive end-to-end multispeaker TTS systems

Ajinkya Kulkarni, Vincent Colotte, Denis Jouvet

Spoken-Text-Style Transfer with Conditional Variational Autoencoder and Content Word Storage

Daiki Yoshioka, Yusuke Yasuda, Noriyuki Matsunaga, Yamato Ohtani, Tomoki Toda

Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks

Lev Finkelstein, Heiga Zen, Norman Casagrande, Chun-An Chan, Ye Jia

Few Shot Cross-Lingual TTS Using Transferable Phoneme Embedding

Wei-Ping Huang, Po-Chun Chen, Sung-Feng Huang, Hung-yi Lee

FluentTTS: Text-dependent Fine-grained Style Control for Multi-style TTS

ChangHwan Kim, Seyun Um, Hyungchan Yoon, Hong-Goo Kang