Interspeech 2022

1,123 papers

Calibrate and Refine! A Novel and Agile Framework for ASR Error Robust Intent Detection

Peilin Zhou, Dading Chong, Helin Wang, Qingcheng Zeng

Contextual Acoustic Barge-In Classification for Spoken Dialog Systems

Dhanush Bekal, Sundararajan Srinivasan, Srikanth Ronanki, Sravan Bodapati, Katrin Kirchhoff

Dialogue Acts Aided Important Utterance Detection Based on Multiparty and Multimodal Information

Fumio Nihei, Ryo Ishii, Yukiko Nakano, Kyosuke Nishida, Ryo Masumura

Induce Spoken Dialog Intents via Deep Unsupervised Context Contrastive Clustering

Ting-Wei Wu, Biing Juang

Reducing Offensive Replies in Open Domain Dialogue Systems

Naokazu Uchida, Takeshi Homma, Makoto Iwayama, Yasuhiro Sogawa

Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR

Takashi Maekaku, Yuya Fujita, Yifan Peng, Shinji Watanabe

Domain Adversarial Self-Supervised Speech Representation Learning for Improving Unknown Domain Downstream Tasks

Tomohiro Tanaka, Ryo Masumura, Hiroshi Sato, Mana Ihori, Kohei Matsuura

From Undercomplete to Sparse Overcomplete Autoencoders to Improve LF-MMI based Speech Recognition

Selen Hande Kabil, Hervé Bourlard

On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training

Jisi Zhang, Cătălin Zorilă, Rama Doddipatla, Jon Barker

Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition

Chenfeng Miao, Kun Zou, Ziyang Zhuang, Tao Wei, Jun Ma

Dealing with Unknowns in Continual Learning for End-to-end Automatic Speech Recognition

Martin Sustek, Samik Sadhu, Hynek Hermansky

CTC Variations Through New WFST Topologies

Aleksandr Laptev, Somshubra Majumdar, Boris Ginsburg

Improving the Training Recipe for a Robust Conformer-based Hybrid Model

Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher, Ralf Schlüter, Hermann Ney

Improving Rare Word Recognition with LM-aware MWER Training

Wang Weiran, Tongzhou Chen, Tara Sainath, Ehsan Variani, Rohit Prabhavalkar

Analysis of Self-Attention Head Diversity for Conformer-based Automatic Speech Recognition

Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno

PM-MMUT: Boosted Phone-mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition

Guodong Ma, Pengfei Hu, Nurmemet Yolwas, Shen Huang, Hao Huang

Leveraging Acoustic Contextual Representation by Audio-textual Cross-modal Learning for Conversational ASR

Kun Wei, Yike Zhang, Sining Sun, Lei Xie, Long Ma

NAS-SCAE: Searching Compact Attention-based Encoders For End-to-end Automatic Speech Recognition

Yukun Liu, Ta Li, Pengyuan Zhang, Yonghong Yan

SCaLa: Supervised Contrastive Learning for End-to-End Speech Recognition

Li Fu, Xiaoxiao Li, Runyu Wang, Lu Fan, Zhengchen Zhang

FedNST: Federated Noisy Student Training for Automatic Speech Recognition

Haaris Mehmood, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay

Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations

Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya

Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation

Manthan Thakker, Sefik Emre Eskimez, Takuya Yoshioka, Huaming Wang

Efficient Speech Enhancement with Neural Homomorphic Synthesis

Wenbin Jiang, Tao Liu, Kai Yu

OSSEM: one-shot speaker adaptive speech enhancement using meta learning

Cheng Yu, Szu-Wei Fu, Tsun-An Hsieh, Yu Tsao, Mirco Ravanelli

Speech Enhancement with Fullband-Subband Cross-Attention Network

Jun Chen, Wei Rao, Zilin Wang, Zhiyong Wu, Yannan Wang

Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention

Xinmeng Xu, Yang Wang, Jie Jia, Binbin Chen, Dejun Li

GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block

Xinmeng Xu, Yang Wang, Jie Jia, Binbin Chen, Jianjun Hao

Memory-Efficient Multi-Step Speech Enhancement with Neural ODE

Jen-Hung Huang, Chung-Hsien Wu

Attentive Recurrent Network for Low-Latency Active Noise Control

Hao Zhang, Ashutosh Pandey, Deliang Wang

Joint Optimization of the Module and Sign of the Spectral Real Part Based on CRN for Speech Denoising.

Zilu Guo, Xu Xu, Zhongfu Ye

Single-channel speech enhancement using Graph Fourier Transform

Chenhui Zhang, Xiang Pan

Model Compression by Iterative Pruning with Knowledge Distillation and Its Application to Speech Enhancement

Zeyuan Wei, Li Hao, Xueliang Zhang

CMGAN: Conformer-based Metric GAN for Speech Enhancement

Ruizhe Cao, Sherif Abdulatif, Bin Yang

Spectro-Temporal SubNet for Real-Time Monaural Speech Denoising and Dereverberation

Feifei Xiong, Weiguang Chen, Pengyu Wang, Xiaofei Li, Jinwei Feng

Jiaming Cheng, Ruiyu Liang, Yue Xie, Li Zhao, Björn Schuller

Lightweight Full-band and Sub-band Fusion Network for Real Time Speech Enhancement

Zhuangqi Chen, Pingjian Zhang

PercepNet+: A Phase and SNR Aware PercepNet for Real-Time Speech Enhancement

Xiaofeng Ge, Jiangyu Han, Yanhua Long, Haixin Guan

TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation

Ali Aroudi, Stefan Uhlich, Marc Ferras Font

VCSE: Time-Domain Visual-Contextual Speaker Extraction Network

Junjie Li, Meng Ge, Zexu Pan, Longbiao Wang, Jianwu Dang

Distance-Based Sound Separation

Katharine Patterson, Kevin Wilson, Scott Wisdom, John R. Hershey

Iterative Sound Source Localization for Unknown Number of Sources

Yanjie Fu, Meng Ge, Haoran Yin, Xinyuan Qian, Longbiao Wang

MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources

Haoran Yin, Meng Ge, Yanjie Fu, Gaoyan Zhang, Longbiao Wang

Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation

Xiaoyu Wang, Xiangyu Kong, Xiulian Peng, Yan Lu

Small Footprint Neural Networks for Acoustic Direction of Arrival Estimation

Zhiheng Ouyang, Miao Wang, Wei-Ping Zhu

How to Listen? Rethinking Visual Sound Localization

Ho-Hsiang Wu, Magdalena Fuentes, Prem Seetharaman, Juan Pablo Bello

Joint Estimation of Direction-of-Arrival and Distance for Arrays with Directional Sensors based on Sparse Bayesian Learning

Feifei Xiong, Pengyu Wang, Zhongfu Ye, Jinwei Feng

Beam-Guided TasNet: An Iterative Speech Separation Framework with Multi-Channel Output

Hangting Chen, Yi Yang, Feng Dang, Pengyuan Zhang

Training Data Generation with DOA-based Selecting and Remixing for Unsupervised Training of Deep Separation Models

Hokuto Munakata, Ryu Takeda, Kazunori Komatani

SKYE: More than a conversational AI

Alzahra Badi, Chungho Park, Minseok Keum, Miguel Alba, Youngsuk Ryu

VAgyojaka: An Annotating and Post-Editing Tool for Automatic Speech Recognition

Rishabh Kumar, Devaraja Adiga, Mayank Kothari, Jatin Dalal, Ganesh Ramakrishnan

Voice2Alliance: Automatic Speaker Diarization and Quality Assurance of Conversational Alignment

Baihan Lin

NeMo Open Source Speaker Diarization System

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

Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation

Reo Yoneyama, YI-CHIAO WU, Tomoki Toda

Simple and Effective Unsupervised Speech Synthesis

Alexander H. Liu, Cheng-I Lai, Wei-Ning Hsu, Michael Auli, Alexei Baevski

Fast Grad-TTS: Towards Efficient Diffusion-Based Speech Generation on CPU

Ivan Vovk, Tasnima Sadekova, Vladimir Gogoryan, Vadim Popov, Mikhail Kudinov

WavThruVec: Latent speech representation as intermediate features for neural speech synthesis

Hubert Siuzdak, Piotr Dura, Pol van Rijn, Nori Jacoby

Fine-grained Noise Control for Multispeaker Speech Synthesis

Karolos Nikitaras, Georgios Vamvoukakis, Nikolaos Ellinas, Konstantinos Klapsas, Konstantinos Markopoulos

EPIC TTS Models: Empirical Pruning Investigations Characterizing Text-To-Speech Models

Perry Lam, Huayun Zhang, Nancy Chen, Berrak Sisman

End-to-end LPCNet: A Neural Vocoder With Fully-Differentiable LPC Estimation

Krishna Subramani, Jean-Marc Valin, Umut Isik, Paris Smaragdis, Arvindh Krishnaswamy

Hierarchical and Multi-Scale Variational Autoencoder for Diverse and Natural Non-Autoregressive Text-to-Speech

Jaesung Bae, Jinhyeok Yang, Taejun Bak, Young-Sun Joo

Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge

Sangjun Park, Kihyun Choo, Joohyung Lee, Anton V. Porov, Konstantin Osipov

SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping

Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani

MSR-NV: Neural Vocoder Using Multiple Sampling Rates

Kentaro Mitsui, Kei Sawada

DRSpeech: Degradation-Robust Text-to-Speech Synthesis with Frame-Level and Utterance-Level Acoustic Representation Learning

Takaaki Saeki, Kentaro Tachibana, Ryuichi Yamamoto

Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus

Minchan Kim, Myeonghun Jeong, Byoung Jin Choi, Sunghwan Ahn, Joun Yeop Lee

Orofacial somatosensory inputs in speech perceptual training modulate speech production

Monica Ashokumar, Jean-Luc Schwartz, Takayuki Ito

Deep Speech Synthesis from Articulatory Representations

Peter Wu, Shinji Watanabe, Louis Goldstein, Alan W Black, Gopala Krishna Anumanchipalli

Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE

Marc-Antoine Georges, Jean-Luc Schwartz, Thomas Hueber

Speech imitation skills predict automatic phonetic convergence: a GMM-UBM study on L2

Dorina de Jong, Aldo Pastore, Noël Nguyen, Alessandro D'Ausilio

Three-dimensional finite-difference time-domain acoustic analysis of simplified vocal tract shapes

Debasish Mohapatra, Mario Fleischer, Victor Zappi, Peter Birkholz, Sidney Fels

Method for improving the word intelligibility of presented speech using bone-conduction headphones

Teruki Toya, Wenyu Zhu, Maori Kobayashi, Kenichi Nakamura, Masashi Unoki

Idiosyncratic lingual articulation of American English /æ/ and /ɑ/ using network analysis

Carolina Lins Machado, Volker Dellwo, Lei He

Low-Level Physiological Implications of End-to-End Learning for Speech Recognition

Louise Coppieters de Gibson, Philip N. Garner

Recurrent multi-head attention fusion network for combining audio and text for speech emotion recognition

Chung-Soo Ahn, Chamara Kasun, Sunil Sivadas, Jagath Rajapakse

Development of allophonic realization until adolescence: A production study of the affricate-fricative variation of /z/ among Japanese children

Sanae Matsui, Kyoji Iwamoto, Reiko Mazuka

Relationship between the acoustic time intervals and tongue movements of German diphthongs

Arne-Lukas Fietkau, Simon Stone, Peter Birkholz

Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network

Ashutosh Pandey, Buye Xu, Anurag Kumar, Jacob Donley, Paul Calamia

Relative Acoustic Features for Distance Estimation in Smart-Homes

Francesco Nespoli, Daniel Barreda, Patrick Naylor

Clustering-based Wake Word Detection in Privacy-aware Acoustic Sensor Networks

Timm Koppelmann, Luca Becker, Alexandru Nelus, Rene Glitza, Lea Schönherr

Practical Over-the-air Perceptual AcousticWatermarking

Ameya Agaskar

Challenges and Opportunities in Multi-device Speech Processing

Gregory Ciccarelli, Jarred Barber, Arun Nair, Israel Cohen, Tao Zhang

Joint Optimization of Sampling Rate Offsets Based on Entire Signal Relationship Among Distributed Microphones

Yoshiki Masuyama, Kouei Yamaoka, Nobutaka Ono

A BERT-based Language Modeling Framework

Chin-Yueh Chien, Kuan-Yu Chen

UserLibri: A Dataset for ASR Personalization Using Only Text

Theresa Breiner, Swaroop Ramaswamy, Ehsan Variani, Shefali Garg, Rajiv Mathews

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition

W. Ronny Huang, Cal Peyser, Tara Sainath, Ruoming Pang, Trevor D. Strohman

Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems

Saket Dingliwal, Ashish Shenoy, Sravan Bodapati, Ankur Gandhe, Ravi Teja Gadde

Space-Efficient Representation of Entity-centric Query Language Models

Christophe Van Gysel, Mirko Hannemann, Ernest Pusateri, Youssef Oualil, Ilya Oparin

Transformer-based quality assessment model for generalized user-generated multimedia audio content

Deebha Mumtaz, Ajit Jena, Vinit Jakhetiya, Karan Nathwani, Sharath Chandra Guntuku

Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning

Salah Zaiem, Titouan Parcollet, Slim Essid

Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization for Fake Audio Detection

Kai Li, Sheng Li, Xugang Lu, Masato Akagi, Meng Liu

An objective test tool for pitch extractors' response attributes

Hideki Kawahara, Kohei Yatabe, Ken-Ichi Sakakibara, Tatsuya Kitamura, Hideki Banno

Speech Quality Assessment through MOS using Non-Matching References

Pranay Manocha, Anurag Kumar

SAQAM: Spatial Audio Quality Assessment Metric

Pranay Manocha, Anurag Kumar, Buye Xu, Anjali Menon, Israel Degene Gebru

Acquisition of allophonic variation in second language speech: An acoustic and articulatory study of English laterals by Japanese speakers

Takayuki Nagamine

Linguistic versus biological factors governing acoustic voice variation

Yoonjeong Lee, Jody Kreiman

Exploration strategies for articulatory synthesis of complex syllable onsets

Daniel van Niekerk, Anqi Xu, Branislav Gerazov, Paul Konstantin Krug, Peter Birkholz

Trajectories predicted by optimal speech motor control using LSTM networks

Tsiky Rakotomalala, Pierre Baraduc, Pascal Perrier

Streaming model for Acoustic to Articulatory Inversion with transformer networks

Sathvik Udupa, Aravind Illa, Prasanta Ghosh

Variability in Production of Non-Sibilant Fricative [ç] in /hi/

Tsukasa Yoshinaga, Kikuo Maekawa, Akiyoshi Iida

Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification

Saurabh Kataria, Jesus Villalba, Laureano Moro-Velazquez, Najim Dehak