Interspeech 2022

1,123 papers

Deep Sparse Conformer for Speech Recognition

Xianchao Wu

Pruned RNN-T for fast, memory-eﬀicient ASR training

Fangjun Kuang, Liyong Guo, Wei Kang, Long Lin, Mingshuang Luo

Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition

Zhifu Gao, Shiliang Zhang, Ian McLoughlin, Zhijie Yan

Efficient Training of Neural Transducer for Speech Recognition

Wei Zhou, Wilfried Michel, Ralf Schlüter, Hermann Ney

Conformer with dual-mode chunked attention for joint online and offline ASR

Felix Weninger, Marco Gaudesi, Md Akmal Haidar, Nicola Ferri, Jesus Andres-Ferrer

Bring dialogue-context into RNN-T for streaming ASR

JunFeng Hou, Jinkun Chen, Wanyu Li, Yufeng Tang, Jun Zhang

Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition

Guangzhi Sun, Chao Zhang, Phil Woodland

Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization

Andrea Fasoli, Chia-Yu Chen, Mauricio Serrano, Swagath Venkataramani, George Saon

Confidence Measure for Automatic Age Estimation From Speech

Amruta Saraf, Ganesh Sivaraman, Elie Khoury

State & Trait Measurement from Nonverbal Vocalizations: A Multi-Task Joint Learning Approach

Alice Baird, Panagiotis Tzirakis, Jeff Brooks, Lauren Kim, Michael Opara

How do our eyebrows respond to masks and whispering? The case of Persians

Nasim Mahdinazhad Sardhaei, Marzena Żygis, Hamid Sharifzadeh

Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals

Jinhan Wang, Vijay Ravi, Jonathan Flint, Abeer Alwan

Context-aware Multimodal Fusion for Emotion Recognition

Jinchao Li, Shuai Wang, Yang Chao, Xunying Liu, Helen Meng

Hierarchical Attention Network for Evaluating Therapist Empathy in Counseling Session

Dehua Tao, Tan Lee, Harold Chui, Sarah Luk

Characterizing Therapist's Speaking Style in Relation to Empathy in Psychotherapy

Dehua Tao, Tan Lee, Harold Chui, Sarah Luk

Exploiting Fine-tuning of Self-supervised Learning Models for Improving Bi-modal Sentiment Analysis and Emotion Recognition

Wei Yang, Satoru Fukayama, Panikos Heracleous, Jun Ogata

Impact of Background Noise and Contribution of Visual Information in Emotion Identification by Native Mandarin Speakers

Minyue Zhang, Hongwei Ding

Audio-Visual Domain Adaptation Feature Fusion for Speech Emotion Recognition

Jie Wei, Guanyu Hu, Xinyu Yang, Anh Tuan Luu, Yizhuo Dong

Exploring Multi-task Learning Based Gender Recognition and Age Estimation for Class-imbalanced Data

Weiqiao Zheng, Ping Yang, Rongfeng Lai, Kongyang Zhu, Tao Zhang

Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model

Tarun Gupta, Tuan Duc Truong, Tran The Anh, Eng Siong Chng

Word-wise Sparse Attention for Multimodal Sentiment Analysis

Fan Qian, Hongwei Song, Jiqing Han

Towards Automated Dialog Personalization using MBTI Personality Indicators

Daniel Fernau, Stefan Hillmann, Nils Feldhus, Tim Polzehl

Differential Time-frequency Log-mel Spectrogram Features for Vision Transformer Based Infant Cry Recognition

Hai-tao Xu, Jie Zhang, Li-Rong Dai

An Automated Mood Diary for Older User’s using Ambient Assisted Living Recorded Speech

Fasih Haider, Saturnino Luz

CoachLea: an Android Application to Evaluate the Speech Production and Perception of Children with Hearing Loss

P. Schäfer, P. A. Pérez-Toro, P. Klumpp, J. R. Orozco-Arroyave, E. Nöth

Coswara: A website application enabling COVID-19 screening by analysing respiratory sound samples and health symptoms

Debarpan Bhattacharya, Debottam Dutta, Neeraj Kumar Sharma, Srikanth Raj Chetupalli, Pravin Mote

Application for Real-time Personalized Speaker Extraction

Damien Ronssin, Milos Cernak

Humanizing bionic voice: interactive demonstration of aesthetic design and control factors influencing the devices assembly and waveshape engineering

Konrad Zieliński, Marek Grzelec, Martin Hagmüller

Real-Time Monitoring of Silences in Contact Center Conversations

Digvijay Ingle, Ayush Kumar, Krishnachaitanya Gogineni, Jithendra Vepa

Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation

Giulia Comini, Goeric Huybrechts, Manuel Sam Ribeiro, Adam Gabryś, Jaime Lorenzo-Trueba

TTS-by-TTS 2: Data-Selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder

Eunwoo Song, Ryuichi Yamamoto, Ohsung Kwon, Chan-Ho Song, Min-Jae Hwang

Vocal effort modeling in neural TTS for improving the intelligibility of synthetic speech in noise

Tuomo Raitio, Petko Petkov, Jiangchuan Li, Muhammed Shifas, Andrea Davis

A Unified Accent Estimation Method Based on Multi-Task Learning for Japanese Text-to-Speech

Byeongseon Park, Ryuichi Yamamoto, Kentaro Tachibana

g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin

Yi-Chang Chen, Yu-Chuan Steven, Yen-Cheng Chang, Yi-Ren Yeh

Challenges of using longitudinal and cross-domain corpora on studies of pathological speech

Catarina Botelho, Tanja Schultz, Alberto Abad, Isabel Trancoso

Enabling Off-the-Shelf Disfluency Detection and Categorization for Pathological Speech

Amrit Romana, Minxue Niu, Matthew Perez, Angela Roberts, Emily Mower Provost

Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression

Salvatore Fara, Stefano Goria, Emilia Molimpakis, Nicholas Cummins

Towards Automated Counselling Decision-Making: Remarks on Therapist Action Forecasting on the AnnoMI Dataset

Zixiu Wu, Rim Helaoui, Diego Reforgiato Recupero, Daniele Riboni

RNN Transducers for Named Entity Recognition with constraints on alignment for understanding medical conversations

Hagen Soltau, Izhak Shafran, Mingqiu Wang, Laurent El Shafey

Improving Voice Trigger Detection with Metric Learning

Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum

Latency Control for Keyword Spotting

Christin Jose, Joe Wang, Grant Strimel, Mohammad Omar Khursheed, Yuriy Mishchenko

Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer

Jan Švec, Jan Lehečka, Luboš Šmídl

Personalized Keyword Spotting through Multi-task Learning

Seunghan Yang, Byeonggeun Kim, Inseop Chung, Simyung Chang

Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings

Badr M. Abdullah, Bernd Möbius, Dietrich Klakow

Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting

Hyeon-Kyeong Shin, Hyewon Han, Doyeon Kim, Soo-Whan Chung, Hong-Goo Kang

Lexical stress in Spanish word segmentation

Alvaro Martin Iturralde Zurita, Meghan Clayards

Why is Korean lenis stop difficult to perceive for L2 Korean learners?

Boram Lee, Naomi Yamaguchi, Cécile Fougeron

Effects of laryngeal manipulations on voice gender perception

Zhaoyan Zhang, Jason Zhang, Jody Kreiman

Factors affecting the percept of Yanny v. Laurel (or mixed): Insights from a large-scale study on Swiss German listeners

Adrian Leemann, Péter Jeszenszky, Carina Steiner, Corinne Lanthemann

Generating iso-accented stimuli for second language research: methodology and a dataset for Spanish-accented English

Rubén Pérez Ramón, Martin Cooke, Maria Luisa Garcia Lecumberri

One-step models in pitch perception: Experimental evidence from Japanese

Takeshi Kishiyama, Chuyu Huang, Yuki Hirose

SVTS: Scalable Video-to-Speech Synthesis

Rodrigo Schoburg Carrillo de Mira, Alexandros Haliassos, Stavros Petridis, Bjorn W. Schuller, Maja Pantic

Exploring Capabilities of Monolingual Audio Transformers using Large Datasets in Automatic Speech Recognition of Czech

Jan Lehečka, Jan Švec, Aleš Pražák, Josef Psutka

Streaming Intended Query Detection using E2E Modeling for Continued Conversation

Shuo-Yiin Chang, Guru Prakash, Zelin Wu, Tara Sainath, Bo Li

Turn-Taking Prediction for Natural Conversational Speech

Shuo-Yiin Chang, Bo Li, Tara Sainath, Chao Zhang, Trevor Strohman

End-to-End Dependency Parsing of Spoken French

Adrien Pupier, Maximin Coavoux, Benjamin Lecouteux, Jérôme Goulian

End-to-end Speech-to-Punctuated-Text Recognition

Jumon Nozaki, Tatsuya Kawahara, Kenkichi Ishizuka, Taiichi Hashimoto

Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain

Dejan Markovic, Alexandre Defossez, Alexander Richard

Separate What You Describe: Language-Queried Audio Source Separation

Xubo Liu, Haohe Liu, Qiuqiang Kong, Xinhao Mei, Jinzheng Zhao

Heterogeneous Target Speech Separation

Efthymios Tzinis, Gordon Wichern, Aswin Shanmugam Subramanian, Paris Smaragdis, Jonathan Le Roux

Extending GCC-PHAT using Shift Equivariant Neural Networks

Axel Berg, Mark O'Connor, Kalle Åström, Magnus Oskarsson

A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction

Zexu Pan, Meng Ge, Haizhou Li

Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation

Qianqian Dong, Fengpeng Yue, Tom Ko, Mingxuan Wang, Qibing Bai

Isochrony-Aware Neural Machine Translation for Automatic Dubbing

Derek Tam, Surafel M. Lakew, Yogesh Virkar, Prashant Mathur, Marcello Federico

From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation

Danni Liu, Changhan Wang, Hongyu Gong, Xutai Ma, Yun Tang

Audio-Visual Speech Recognition in MISP2021 Challenge: Dataset Release and Deep Analysis

Hang Chen, Jun Du, Yusheng Dai, Chin-Hui Lee, Sabato Marco Siniscalchi

Bayesian Transformer Using Disentangled Mask Attention

Jen-Tzung Chien, Yu-Han Huang

Biometric Russian Audio-Visual Extended MASKS (BRAVE-MASKS) Corpus: Multimodal Mask Type Recognition Task

Maxim Markitantov, Elena Ryumina, Dmitry Ryumin, Alexey Karpov

BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese

Nguyen Luong Tran, Duong Le, Dat Quoc Nguyen

Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation

Keqi Deng, Shinji Watanabe, Jiatong Shi, Siddhant Arora

TALCS: An open-source Mandarin-English code-switching corpus and a speech recognition baseline

Chengfei Li, Shuhao Deng, Yaoping Wang, Guangjing Wang, Yaguang Gong

Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset

Zehui Yang, Yifan Chen, Lei Luo, Runyan Yang, Lingxuan Ye

Investigating Parameter Sharing in Multilingual Speech Translation

Qian Wang, Chen Wang, Jiajun Zhang

A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation

Linh The Nguyen, Nguyen Luong Tran, Long Doan, Manh Luong, Dat Quoc Nguyen

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation

Ye Jia, Yifan Ding, Ankur Bapna, Colin Cherry, Yu Zhang

Self-Distillation Based on High-level Information Supervision for Compressing End-to-End ASR Model

Qiang Xu, Tongtong Song, Longbiao Wang, Hao Shi, Yuqin Lin

4-bit Conformer with Native Quantization Aware Training for Speech Recognition

Shaojin Ding, Phoenix Meadowlark‎, Yanzhang He, Lukasz Lew, Shivani Agrawal

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

Shaojin Ding, Wang Weiran, Ding Zhao, Tara Sainath, Yanzhang He

Federated Pruning: Improving Neural Network Efficiency with Federated Learning

Rongmei Lin, Yonghui Xiao, Tien-Ju Yang, Ding Zhao, Li Xiong

Streaming Align-Refine for Non-autoregressive Deliberation

Wang Weiran, Ke Hu, Tara Sainath

Multi-stage Progressive Compression of Conformer Transducer for On-device Speech Recognition

Jash Rathod, Nauman Dawalatabad, Shatrughan Singh, Dhananjaya Gowda

LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT

Rui Wang, Qibing Bai, Junyi Ao, Long Zhou, Zhixiang Xiong

CaTT-KWS: A Multi-stage Customized Keyword Spotting Framework based on Cascaded Transducer-Transformer

Zhanheng Yang, Sining Sun, Jin Li, Xiaoming Zhang, Xiong Wang

Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

Ye Bai, Jie Li, Wenjing Han, Hao Ni, Kaituo Xu

Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies

Zehan Li, Haoran Miao, Keqi Deng, Gaofeng Cheng, Sanli Tian

Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR

Yufei Liu, Rao Ma, Haihua Xu, Yi He, Zejun Ma

WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit

Binbin Zhang, Di Wu, Zhendong Peng, Xingchen Song, Zhuoyuan Yao

VQ-T: RNN Transducers using Vector-Quantized Prediction Network States

Jiatong Shi, George Saon, David Haws, Shinji Watanabe, Brian Kingsbury

Learning to rank with BERT-based confidence models in ASR rescoring

Ting-Wei Wu, I-Fan Chen, Ankur Gandhe

On Adaptive Weight Interpolation of the Hybrid Autoregressive Transducer

Ehsan Variani, Michael Riley, David Rybach, Cyril Allauzen, Tongzhou Chen

Diffusion Generative Vocoder for Fullband Speech Synthesis Based on Weak Third-order SDE Solver

Hideyuki Tachibana, Muneyoshi Inahara, Mocho Go, Yotaro Katayama, Yotaro Watanabe

A compact transformer-based GAN vocoder

Chenfeng Miao, Ting Chen, Minchuan Chen, Jun Ma, Shaojun Wang

MISRNet: Lightweight Neural Vocoder Using Multi-Input Single Shared Residual Blocks

Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki

Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU

Hiroki Kanagawa, Yusuke Ijima, Hiroyuki Toda

Text-to-speech synthesis using spectral modeling based on non-negative autoencoder

Takeru Gorai, Daisuke Saito, Nobuaki Minematsu

SiD-WaveFlow: A Low-Resource Vocoder Independent of Prior Knowledge

Yuhan Li, Ying Shen, Dongqing Wang, Lin Zhang

A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS

Haohan Guo, Feng-Long Xie, Frank Soong, Xixin Wu, Helen Meng

SoftSpeech: Unsupervised Duration Model in FastSpeech 2

Yuan-Hao Yi, Lei He, Shifeng Pan, Xi Wang, Yuchao Zhang

Improving GAN-based vocoder for fast and high-quality speech synthesis

He Mengnan, Tingwei Guo, Zhenxing Lu, Zhang Ruixiong, Gong Caixia

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature

Chenpeng Du, Yiwei Guo, Xie Chen, Kai Yu