Interspeech 2022

1,123 papers

Investigating the contribution of speaker attributes to speaker separability using disentangled speaker representations

Chau Luu, Steve Renals, Peter Bell

Training speaker embedding extractors using multi-speaker audio with unknown speaker boundaries

Themos Stafylakis, Ladislav Mošner, Oldřich Plchot, Johan Rohdin, Anna Silnova

Scoring of Large-Margin Embeddings for Speaker Verification: Cosine or PLDA?

Qiongqiong Wang, Kong Aik Lee, TIANCHI LIU

Domain Agnostic Few-shot Learning for Speaker Verification

Seunghan Yang, Debasmit Das, Janghoon Cho, Hyoungwoo Park, Sungrack Yun

Extended U-Net for Speaker Verification in Noisy Environments

Ju-ho Kim, Jungwoo Heo, Hye-jin Shim, Ha-Jin Yu

End-to-End Multi-Loss Training for Low Delay Packet Loss Concealment

Nan Li, Xiguang Zheng, Chen Zhang, Liang Guo, Bing Yu

INTERSPEECH 2022 Audio Deep Packet Loss Concealment Challenge

Lorenz Diener, Sten Sootla, Solomiya Branets, Ando Saabas, Robert Aichner

PLCNet: Real-time Packet Loss Concealment with Semi-supervised Generative Adversarial Network

Baiyun Liu, Qi Song, Mingxue Yang, Wuwen Yuan, Tianbao Wang

Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model

Jean-Marc Valin, Ahmed Mustafa, Christopher Montgomery, Timothy B. Terriberry, Michael Klingbeil

TMGAN-PLC: Audio Packet Loss Concealment using Temporal Memory Generative Adversarial Network

Yuansheng Guan, Guochen Yu, Andong Li, Chengshi Zheng, Jie Wang

A Comparative Study on Speaker-attributed Automatic Speech Recognition in Multi-party Meetings

Fan Yu, Zhihao Du, Shiliang Zhang, Yuxiao Lin, Lei Xie

Leveraging Prosody for Punctuation Prediction of Spontaneous Speech

Yeonjin Cho, Sara Ng, Trang Tran, Mari Ostendorf

Thutmose Tagger: Single-pass neural model for Inverse Text Normalization

Alexandra Antonova, Evelina Bakhturina, Boris Ginsburg

Extending RNN-T-based speech recognition systems with emotion and language classification

Zvi Kons, Hagai Aronowitz, Edmilson Morais, Matheus Damasceno, Hong-Kwang Kuo

Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer's Speech Detection

Longfei Yang, Wenqing Wei, Sheng Li, Jiyi Li, Takahiro Shinozaki

Federated Domain Adaptation for ASR with Full Self-Supervision

Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation

Yi-Kai Zhang, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

Speaker consistency loss and step-wise optimization for semi-supervised joint training of TTS and ASR using unpaired text data

Naoki Makishima, Satoshi Suzuki, Atsushi Ando, Ryo Masumura

Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings

Naoyuki Kanda, Jian Wu, Yu Wu, Xiong Xiao, Zhong Meng

Binary Early-Exit Network for Adaptive Inference on Low-Resource Devices

Aaqib Saeed

Visualising Model Training via Vowel Space for Text-To-Speech Systems

Binu Nisal Abeysinghe, Jesin James, Catherine Watson, Felix Marattukalam

CAUSE: Crossmodal Action Unit Sequence Estimation from Speech

Hirokazu Kameoka, Takuhiro Kaneko, Shogo Seki, Kou Tanaka

A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis

Qibing Bai, Tom Ko, Yu Zhang

Prosodic alignment for off-screen automatic dubbing

Yogesh Virkar, Marcello Federico, Robert Enyedi, Roberto Barra-Chicote

Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization

Evelina Bakhturina, Yang Zhang, Boris Ginsburg

SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation

Artem Ploujnikov, Mirco Ravanelli

Environment Aware Text-to-Speech Synthesis

Daxin Tan, Guangyan Zhang, Tan Lee

An Automatic Soundtracking System for Text-to-Speech Audiobooks

Zikai Chen, Lin Wu, Junjie Pan, Xiang Yin

Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks

Cassia Valentini-Botinhao, Manuel Sam Ribeiro, Oliver Watts, Korin Richmond, Gustav Eje Henter

An Efficient and High Fidelity Vietnamese Streaming End-to-End Speech Synthesis

Tho Nguyen Duc Tran, The Chuong Chu, Vu Hoang, Trung Huu Bui, Hung Quoc Truong

Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition

Junrui Ni, Liming Wang, Heting Gao, Kaizhi Qian, Yang Zhang

Mixed-Phoneme BERT: Improving BERT with Mixed Phoneme and Sup-Phoneme Representations for Text to Speech

Guangyan Zhang, Kaitao Song, Xu Tan, Daxin Tan, Yuzi Yan

DocLayoutTTS: Dataset and Baselines for Layout-informed Document-level Neural Speech Synthesis

Puneet Mathur, Franck Dernoncourt, Quan Hung Tran, Jiuxiang Gu, Ani Nenkova

ByT5 model for massively multilingual grapheme-to-phoneme conversion

Jian Zhu, Cong Zhang, David Jurgens

Neural Lexicon Reader: Reduce Pronunciation Errors in End-to-end TTS by Leveraging External Textual Knowledge

Mutian He, Jingzhou Yang, Lei He, Frank Soong

A polyphone BERT for Polyphone Disambiguation in Mandarin Chinese

Song Zhang, Ken Zheng, Xiaoxu Zhu, Baoxiang Li

SpeechPainter: Text-conditioned Speech Inpainting

Zalán Borsos, Matthew Sharifi, Marco Tagliasacchi

Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information

Jie Chen, Changhe Song, Deyi Tuo, Xixin Wu, Shiyin Kang

EdiTTS: Score-based Editing for Controllable Text-to-Speech

Jaesung Tae, Hyeongju Kim, Taesu Kim

Dataset Pruning for Resource-constrained Spoofed Audio Detection

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models

Takanori Ashihara, Takafumi Moriya, Kohei Matsuura, Tomohiro Tanaka

Predicting label distribution improves non-intrusive speech quality estimation

Abu Zaher Md Faridee, Hannes Gamper

Densely-connected Convolutional Recurrent Network for Fundamental Frequency Estimation in Noisy Speech

YIXUAN ZHANG, Heming Wang, Deliang Wang

Learning neural audio features without supervision

Sarthak Yadav, Neil Zeghidour

Generative Data Augmentation Guided by Triplet Loss for Speech Emotion Recognition

Shijun Wang, Hamed Hemati, Jón Guðnason, Damian Borth

Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load

Gasser Elbanna, Alice Biryukov, Neil Scheidwasser-Clow, Lara Orlandic, Pablo Mainar

PEAF: Learnable Power Efficient Analog Acoustic Features for Audio Recognition

Boris Bergsma, Minhao Yang, Milos Cernak

Audio Anti-spoofing Using Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning

John H.L. Hansen, Zhenyu Wang

Deep Transductive Transfer Regression Network for Cross-Corpus Speech Emotion Recognition

Yan Zhao, Jincen Wang, Ru Ye, Yuan Zong, Wenming Zheng

A Sparsity-promoting Dictionary Model for Variational Autoencoders

Mostafa Sadeghi, Paul Magron

Global Signal-to-noise Ratio Estimation Based on Multi-subband Processing Using Convolutional Neural Network

Nan Li, Meng Ge, Longbiao Wang, Masashi Unoki, Sheng Li

TRILLsson: Distilled Universal Paralinguistic Speech Representations

Joel Shor, Subhashini Venugopalan

VoiceLab: Software for Fully Reproducible Automated Voice Analysis

David Feinberg

SpeechFormer: A Hierarchical Efficient Framework Incorporating the Characteristics of Speech

Weidong Chen, Xiaofen Xing, Xiangmin Xu, Jianxin Pang, Lan Du

CTFALite: Lightweight Channel-specific Temporal and Frequency Attention Mechanism for Enhancing the Speaker Embedding Extractor

Yuheng Wei, Junzhao Du, Hui LIU, Qian Wang

Unifying Cosine and PLDA Back-ends for Speaker Verification

Zhiyuan Peng, Xuanji He, Ke Ding, Tan Lee, Guanglu Wan

Reliable Visualization for Deep Speaker Recognition

Pengqi Li, Lantian Li, Askar Hamdulla, Dong Wang

CS-CTCSCONV1D: Small footprint speaker verification with channel split time-channel-time separable 1-dimensional convolution

Linjun Cai, Yuhong Yang, Xufeng Chen, Weiping Tu, Hongyang Chen

Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning

Mufan Sang, John H.L. Hansen

Transport-Oriented Feature Aggregation for Speaker Embedding Learning

Yusheng Tian, Jingyu Li, Tan Lee

Enroll-Aware Attentive Statistics Pooling for Target Speaker Verification

Leying Zhang, Zhengyang Chen, Yanmin Qian

MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification

Yang Zhang, Zhiqiang Lv, Haibin Wu, Shanshan Zhang, Pengfei Hu

Adaptive Rectangle Loss for Speaker Verification

Li Ruida, Fang Shuo, Ma Chenguang, Li Liang

DF-ResNet: Boosting Speaker Verification Performance with Depth-First Design

Bei Liu, Zhengyang Chen, Shuai Wang, Haoyu Wang, Bing Han

Dual Path Embedding Learning for Speaker Verification with Triplet Attention

Bei Liu, Zhengyang Chen, Yanmin Qian

Attentive Feature Fusion for Robust Speaker Verification

Bei Liu, Zhengyang Chen, Yanmin Qian

Reliability criterion based on learning-phase entropy for speaker recognition with neural network

Pierre-Michel Bousquet, Mickael Rouvier, Jean-Francois Bonastre

Prototypical speaker-interference loss for target voice separation using non-parallel audio samples

Seongkyu Mun, Dhananjaya Gowda, Jihwan Lee, Changwoo Han, Dokyun Lee

An Initialization Scheme for Meeting Separation with Spatial Mixture Models

Christoph Boeddeker, Tobias Cord-Landwehr, Thilo von Neumann, Reinhold Haeb-Umbach

Modelling Turn-taking in Multispeaker Parties for Realistic Data Simulation

Jack Deadman, Jon Barker

NTF of Spectral and Spatial Features for Tracking and Separation of Moving Sound Sources in Spherical Harmonic Domain

Mateusz Guzik, Konrad Kowalczyk

Blind Language Separation: Disentangling Multilingual Cocktail Party Voices by Language

Marvin Borsdorf, Kevin Scheck, Haizhou Li, Tanja Schultz

Unsupervised Training of Sequential Neural Beamformer Using Coarsely-separated and Non-separated Signals

Kohei Saijo, Tetsuji Ogawa

Effect of Head Orientation on Speech Directivity

Samuel Bellows, Timothy W. Leishman

Spatial Loss for Unsupervised Multi-channel Source Separation

Kohei Saijo, Robin Scheibler

Independence-based Joint Dereverberation and Separation with Neural Source Model

Kohei Saijo, Robin Scheibler

PodcastMix: A dataset for separating music and speech in podcasts

Nicolas Schmidt, Jordi Pons, Marius Miron

Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments

Jean-Marie Lemercier, Joachim Thiemann, Raphael Koning, Timo Gerkmann

Monaural Speech Enhancement Based on Spectrogram Decomposition for Convolutional Neural Network-sensitive Feature Extraction

Hao Shi, Longbiao Wang, Sheng Li, Jianwu Dang, Tatsuya Kawahara

Listen only to me! How well can target speech extraction handle false alarms?

Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Kateřina Žmolíková, Hiroshi Sato

Perceptual Characteristics Based Multi-objective Model for Speech Enhancement

Chiang-Jen Peng, Yun-Ju Chan, Yih-Liang Shen, Cheng Yu, Yu Tsao

Improved Modulation-Domain Loss for Neural-Network-based Speech Enhancement

Tyler Vuong, Richard Stern

Attentive Training: A New Training Framework for Talker-independent Speaker Extraction

Ashutosh Pandey, Deliang Wang

CycleGAN-based Unpaired Speech Dereverberation

Hannah Muckenhirn, Aleksandr Safin, Hakan Erdogan, Félix de Chaumont Quitry, Marco Tagliasacchi

Monoaural Speech Enhancement Using a Nested U-Net with Two-Level Skip Connections

Seorim Hwang, Sung Wook Park, Youngcheol Park

Boosting Self-Supervised Embeddings for Speech Enhancement

Kuo-Hsuan Hung, Szu-Wei Fu, Huan-Hsin Tseng, Hsin-Tien Chiang, Yu Tsao

iDeepMMSE: An improved deep learning approach to MMSE speech and noise power spectrum estimation for speech enhancement

Minseung Kim, Hyungchan Song, Sein Cheong, Jong Won Shin

Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement

Tuan Vu Ho, Quoc Huy Nguyen, Masato Akagi, Masashi Unoki

Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion

Tuan Vu Ho, Maori Kobayashi, Masato Akagi

Positional Encoding for Capturing Modality Specific Cadence for Emotion Detection

Hira Dhamyal, Bhiksha Raj, Rita Singh

Exploiting Co-occurrence Frequency of Emotions in Perceptual Evaluations To Train A Speech Emotion Classifier

Huang-Cheng Chou, Chi-Chun Lee, Carlos Busso

Mind the gap: On the value of silence representations to lexical-based speech emotion recognition

Matthew Perez, Mimansa Jaiswal, Minxue Niu, Cristina Gorrostieta, Matthew Roddy

End-To-End Label Uncertainty Modeling for Speech-based Arousal Recognition Using Bayesian Neural Networks

Navin Raj Prabhu, Guillaume Carbajal, Nale Lehmann-Willenbrock, Timo Gerkmann

Probing speech emotion recognition transformers for linguistic knowledge

Andreas Triantafyllopoulos, Johannes Wagner, Hagen Wierstorf, Maximilian Schmitt, Uwe Reichel

The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation

Joosung Lee

Improving Speech Emotion Recognition Through Focus and Calibration Attention Mechanisms

Junghun Kim, Yoojin An, Jihie Kim

Multi-Corpus Speech Emotion Recognition for Unseen Corpus Using Corpus-Wise Weights in Classification Loss

Youngdo Ahn, Sung Joo Lee, Jong Won Shin

Generalized Keyword Spotting using ASR embeddings

Kirandevraj R, Vinod Kumar Kurmi, Vinay Namboodiri, C V Jawahar

Speech Segmentation Optimization using Segmented Bilingual Speech Corpus for End-to-end Speech Translation

Ryo Fukuda, Katsuhito Sudoh, Satoshi Nakamura

Cross-Modal Decision Regularization for Simultaneous Speech Translation

Mohd Abbas Zaidi, Beomseok Lee, Sangha Kim, Chanwoo Kim