Interspeech 2022

1,123 papers

A Vietnamese-English Neural Machine Translation System

Tuan-Duy H. Nguyen, Duy Phung, Duy Tran-Cong Nguyen, Hieu Minh Tran, Manh Luong

Improve emotional speech synthesis quality by learning explicit and implicit representations with semi-supervised training

Jiaxu He, Cheng Gong, Longbiao Wang, Di Jin, Xiaobao Wang

CALM: Constrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis

Yi Meng, Xiang Li, Zhiyong Wu, Tingtian Li, Zixun Sun

Towards Cross-speaker Reading Style Transfer on Audiobook Dataset

Xiang Li, Changhe Song, Xianhao Wei, Zhiyong Wu, Jia Jia

Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis

Shun Lei, Yixuan Zhou, Liyang Chen, Jiankun Hu, Zhiyong Wu

Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis

Yixuan Zhou, Changhe Song, Jingbei Li, Zhiyong Wu, Yanyao Bian

Automatic Prosody Annotation with Pre-Trained Text-Speech Model

Ziqian Dai, Jianwei Yu, Yan Wang, Nuo Chen, Yanyao Bian

Integrating Discrete Word-Level Style Variations into Non-Autoregressive Acoustic Models for Speech Synthesis

Zhaoci Liu, Ningqian Wu, Yajie Zhang, Zhenhua Ling

Self-supervised Context-aware Style Representation for Expressive Speech Synthesis

Yihan Wu, Xi Wang, Shaofei Zhang, Lei He, Ruihua Song

Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis

Tao Li, Xinsheng Wang, Qicong Xie, Zhichao Wang, Mingqi Jiang

Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning

Rui Liu, Berrak Sisman, Björn Schuller, Guanglai Gao, Haizhou Li

Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis

Raul Fernandez, David Haws, Guy Lorberbom, Slava Shechtman, Alexander Sorin

Improve Speech Enhancement using Perception-High-Related Time-Frequency Loss

Ding Zhao, Zhan Zhang, Bin Yu, Yuehai Wang

DCTCN:Deep Complex Temporal Convolutional Network for Long Time Speech Enhancement

Ren Jigang, Mao Qirong

Speech Modification for Intelligibility in Cochlear Implant Listeners: Individual Effects of Vowel- and Consonant-Boosting

Juliana N. Saba, John H.L. Hansen

Steering vector correction in MVDR beamformer for speech enhancement

Suliang Bu, Yunxin Zhao, Tuo Zhao

MTI-Net: A Multi-Target Speech Intelligibility Prediction Model

Ryandhimas Edo Zezario, Szu-Wei Fu, Fei Chen, Chiou-shann Fuh, Hsin-Min Wang

ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding

Yen-Ju Lu, Xuankai Chang, Chenda Li, Wangyou Zhang, Samuele Cornell

A speech enhancement method for long-range speech acquisition task

YANZHANG GENG, Heng Wang, Tao Zhang, Xin Zhao

Perceptual Contrast Stretching on Target Feature for Speech Enhancement

Rong Chao, Cheng Yu, Szu-Wei Fu, Xugang Lu, Yu Tsao

Fusion of Self-supervised Learned Models for MOS Prediction

Zhengdong Yang, Wangjin Zhou, Chenhui Chu, Sheng Li, Raj Dabre

A Transfer and Multi-Task Learning based Approach for MOS Prediction

Xiaohai Tian, Kaiqi Fu, Shaojun Gao, Yiwei Gu, Kai Wang

Fully Automatic Balance between Directivity Factor and White Noise Gain for Large-scale Microphone Arrays in Diffuse Noise Fields

Weixin Meng, Chengshi Zheng, Xiaodong Li

Convolutional Recurrent Smart Speech Enhancement Architecture for Hearing Aids

Soha Nossier, Julie Wall, Mansour Moniri, Cornelius Glackin, Nigel Cannings

Multi-source wideband DOA estimation method by frequency focusing and error weighting

Jing Zhou, Changchun Bao

How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR

Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato

TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor’s Approximation Theory

Andong Li, Guochen Yu, Chengshi Zheng, Xiaodong Li

An Empirical Analysis on the Vulnerabilities of End-to-End Speech Segregation Models

Rahil Parikh, Gaspar Rochette, Carol Espy-Wilson, Shihab Shamma

Text-Driven Separation of Arbitrary Sounds

Kevin Kilgour, Beat Gfeller, Qingqing Huang, Aren Jansen, Scott Wisdom

Cooperative Speech Separation With a Microphone Array and Asynchronous Wearable Devices

Ryan Corey, Manan Mittal, Kanad Sarkar, Andrew C. Singer

Speech Separation for an Unknown Number of Speakers Using Transformers With Encoder-Decoder Attractors

Srikanth Raj Chetupalli, Emanuël Habets

Directed speech separation for automatic speech recognition of long form conversational speech

Rohit Paturi, Sundararajan Srinivasan, Katrin Kirchhoff, Daniel Garcia-Romero

Separating Long-Form Speech with Group-wise Permutation Invariant Training

Wangyou Zhang, Zhuo Chen, Naoyuki Kanda, Shujie LIU, Jinyu Li

Multichannel Speech Separation with Narrow-band Conformer

Changsheng Quan, Xiaofei Li

WA-Transformer: Window Attention-based Transformer with Two-stage Strategy for Multi-task Audio Source Separation

Yang Wang, Chenxing Li, Feng Deng, Shun Lu, Peng Yao

Gated Convolutional Fusion for Time-Domain Target Speaker Extraction Network

Wenjing Liu, Chuan Xie

ResectNet: An Efficient Architecture for Voice Activity Detection on Mobile Devices

Okan Köpüklü, Maja Taseska

Conformer Space Neural Architecture Search for Multi-Task Audio Separation

Shun Lu, Yang Wang, Peng Yao, Chenxing Li, Jianchao Tan

QDPN - Quasi-dual-path Network for single-channel Speech Separation

Joel Rixen, Matthias Renz

Objective Metrics to Evaluate Residual-Echo Suppression During Double-Talk in the Stereophonic Case

Amir Ivry, Israel Cohen, Baruch Berdugo

Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks

Fan-Lin Wang, Hung-Shin Lee, Yu Tsao, Hsin-Min Wang

Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation

Xue Yang, Changchun Bao

Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches

Zifeng Zhao, Dongchao Yang, Rongzhi Gu, Haoran Zhang, Yuexian Zou

On the Use of Deep Mask Estimation Module for Neural Source Separation Systems

Kai Li, Xiaolin Hu, Yi Luo

SepIt: Approaching a Single Channel Speech Separation Bound

Shahar Lutati, Eliya Nachmani, Lior Wolf

Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction

Zifeng Zhao, Rongzhi Gu, Dongchao Yang, Jinchuan Tian, Yuexian Zou

Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation

Jian Luo, Jianzong Wang, Ning Cheng, Edward Xiao, Xulong Zhang

Low-resource Accent Classification in Geographically-proximate Settings: A Forensic and Sociophonetics Perspective

Qingcheng Zeng, Dading Chong, Peilin Zhou, jie Yang

Paraguayan Guarani: Tritonal pitch accent and Accentual Phrase

Sun-Ah Jun, Maria Luisa Zubizarreta

Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data

Gasper Begus, Alan Zhou

High level feature fusion in forensic voice comparison

Michael Carne, Yuko Kinoshita, Shunichi Ishihara

Contribution of the glottal flow residual in affect-related voice transformation

Zihan Wang, Christer Gobl

The Prosody of Cheering in Sport Events

Marzena Żygis, Sarah Wesolek, Nina Hosseini-Kivanani, Manfred Krifka

A Laryngographic Study on the Voice Quality of Northern Vietnamese Tones under the Lombard Effect

Giang Le, Chilin Shih, Yan Tang

Mandarin Tone Sandhi Realization: Evidence from Large Speech Corpora

Zuoyu Tian, Xiao Dong, Feier Gao, Haining Wang, Charles Lin

A blueprint for using deepfakes in sociolinguistic matched-guise experiments

Nathan Joel Young, David Britain, Adrian Leemann

Effects of Language Contact on Vowel Nasalization in Wenzhou and Rugao Dialects

Yan Li, Ying Chen, XINYA ZHANG, Yanyang Chen, Jiazheng Wang

Applying Syntax–Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis

Kei Furukawa, Takeshi Kishiyama, Satoshi Nakamura

Convolutional Neural Networks for Classification of Voice Qualities from Speech and Neck Surface Accelerometer Signals

Sudarsana Reddy Kadiri, Farhad Javanmardi, Paavo Alku

Durational Patterning at Discourse Boundaries in Relation to Therapist Empathy in Psychotherapy

Jonathan Him Nok Lee, Dehua Tao, Harold Chui, Tan Lee, Sarah Luk

Reducing uncertainty at the score-to-LR stage in likelihood ratio-based forensic voice comparison using automatic speaker recognition systems

Bruce Xiao Wang, Vincent Hughes

Eliciting and evaluating likelihood ratios for speaker recognition by human listeners under forensically realistic channel-mismatched conditions

Vincent Hughes, Carmen Llamas, Thomas Kettig

Bending the string: intonation contour length as a correlate of macro-rhythm

Constantijn Kaland

Mandarin nasal place assimilation revisited: an acoustic study

Mingqiong Luo

Native phonotactic interference in L2 vowel processing: Mouse-tracking reveals cognitive conflicts during identification

Yizhou Wang, Rikke Bundgaard-Nielsen, Brett Baker, Olga Maxwell

Improving Data Driven Inverse Text Normalization using Data Augmentation and Machine Translation

Debjyoti Paul, Yutong Pang, Szu-Jui Chen, Xuedong Zhang

Voice Puppetry with FastPitch

Emelie Van De Vreken, Korin Richmond, Catherine Lai

OCTRA – An Innovative Approach to Orthographic Transcription

Christoph Draxler, Julian Pomp

Spoken Dialogue System for Call Centers with Expressive Speech Synthesis

Dāvis Nicmanis, Askars Salimbajevs

Challenges in Metadata Creation for Massive Naturalistic Team-Based Audio Data

Chelzy Belitz, John H.L. Hansen

DyConvMixer: Dynamic Convolution Mixer Architecture for Open-Vocabulary Keyword Spotting

Waseem Gharbieh, Jinmiao Huang, Qianhui Wan, Han Suk Shim, Hyun Chul Lee

QbyE-MLPMixer: Query-by-Example Open-Vocabulary Keyword Spotting using MLPMixer

Jinmiao Huang, Waseem Gharbieh, Qianhui Wan, Han Suk Shim, Hyun Chul Lee

Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation

Sravya Popuri, Peng-Jen Chen, Changhan Wang, Juan Pino, Yossi Adi

Voice Activity Projection: Self-supervised Learning of Turn-taking Events

Erik Ekstedt, Gabriel Skantze

DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances

Sreyan Ghosh, Samden Lepcha, S Sakshi, Rajiv Ratn Shah, Srinivasan Umesh

Building Vietnamese Conversational Smart Home Dataset and Natural Language Understanding Model

Thi Thu Trang NGUYEN, Trung Duc Anh Dang, Quoc Viet Vu, Woomyoung Park

Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation

Chih-Chiang Chang, Hung-yi Lee

Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings

Myunghun Jung, Hoi Rin Kim

DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering

Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung, Shu-wen Yang, Hsuan-Jui Chen

kidsTALC: A Corpus of 3- to 11-year-old German Children’s Connected Natural Speech

Lars Rumberg, Christopher Gebauer, Hanna Ehlert, Maren Wallbaum, Lena Bornholt

STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent

Yuki Saito, Yuto Nishimura, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari

Dynamic Sliding Window Modeling for Abstractive Meeting Summarization

Zhengyuan Liu, Nancy Chen

Investigation of Ensemble features of Self-Supervised Pretrained Models for Automatic Speech Recognition

A Arunkumar, Vrunda Nileshkumar Sukhadia, Srinivasan Umesh

InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR

Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida

Scaling ASR Improves Zero and Few Shot Learning

Weiyi Zheng, Alex Xiao, Gil Keren, Duc Le, Frank Zhang

Wav2vec behind the Scenes: How end2end Models learn Phonetics

Teena tom Dieck, Paula Andrea Pérez-Toro, Tomas Arias, Elmar Noeth, Philipp Klumpp

A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization

Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg

Unsupervised domain adaptation for speech recognition with unsupervised error correction

Long Mai, Julie Carson-berndsen

Using Data Augmentation and Consistency Regularization to Improve Semi-supervised Speech Recognition

Ashtosh Sapru

Learnable Sparse Filterbank for Speaker Verification

Junyi Peng, Rongzhi Gu, Ladislav Mošner, Oldřich Plchot, Lukas Burget

Light-Weight Speaker Verification with Global Context Information

MISEUL KIM, ZHENYU PIAO, Seyun Um, Ran Lee, Jaemin Joh

Can Humans Correct Errors From System? Investigating Error Tendencies in Speaker Identification Using Crowdsourcing

Yuta Ide, Susumu Saito, Teppei Nakano, Tetsuji Ogawa

From Simulated Mixtures to Simulated Conversations as Training Data for End-to-End Neural Diarization

Federico Landini, Alicia Lozano-Diez, Mireia Diez, Lukas Burget

End-to-End Neural Speaker Diarization with an Iterative Refinement of Non-Autoregressive Attention-based Attractors

Magdalena Rybicka, Jesus Villalba, Najim Dehak, Konrad Kowalczyk

Improved Relation Networks for End-to-End Speaker Verification and Identification

Ashutosh Chaubey, Sparsh Sinha, Susmita Ghose

Multi-scale Speaker Diarization with Dynamic Scale Weighting

Tae Jin Park, Nithin Rao Koluguri, Jagadeesh Balam, Boris Ginsburg

Multimodal Clustering with Role Induced Constraints for Speaker Diarization

Nikolaos Flemotomos, Shrikanth Narayanan

Automatic Speaker Verification System for Dysarthria Patients

Shinimol Salim, Syed Shahnawazuddin, Waquar Ahmad

Online Learning of Open-set Speaker Identification by Active User-registration

EunKyung Yoo, Hyeonseop Song, Taehyeong Kim, Chul Lee

AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification

Sonal Joshi, Saurabh Kataria, Jesus Villalba, Najim Dehak