Audio and Speech Processing

Authors and titles for eess.AS in Feb 2021

[1]  arXiv:2102.00154 [pdf, ps, other]

Title: Semi-supervised Sound Event Detection using Random Augmentation and Consistency Regularization

Authors: Xiaofei Li

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[2]  arXiv:2102.00184 [pdf, other]

Title: Adversarially learning disentangled speech representations for robust multi-factor voice conversion

Authors: Jie Wang, Jingbei Li, Xintao Zhao, Zhiyong Wu, Shiyin Kang, Helen Meng

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[3]  arXiv:2102.00196 [pdf, ps, other]

Title: Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech Mixtures

Authors: Karn Watcharasupat, Anh H. T. Nguyen, Ching-Hui Ooi, Andy W. H. Khong

Comments: (c) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Journal-ref: Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 4485-4489

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Signal Processing (eess.SP)

[4]  arXiv:2102.00270 [pdf, other]

Title: Enhancing the Intelligibility of Cleft Lip and Palate Speech using Cycle-consistent Adversarial Networks

Authors: Protima Nomo Sudro, Rohan Kumar Das, Rohit Sinha, S R Mahadeva Prasanna

Comments: 8 pages, 4 figures, IEEE spoken language and technology workshop

Subjects: Audio and Speech Processing (eess.AS)

[5]  arXiv:2102.00306 [pdf, other]

Title: End-to-End Language Identification using Multi-Head Self-Attention and 1D Convolutional Neural Networks

Authors: Krishna D N, Ankita Patil

Comments: 5 pages, 1 figure

Subjects: Audio and Speech Processing (eess.AS)

[6]  arXiv:2102.00804 [pdf, other]

Title: Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript

Authors: Mukuntha Narayanan Sundararaman, Ayush Kumar, Jithendra Vepa

Comments: Accepted to Interspeech 2021 conference

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL)

[7]  arXiv:2102.00850 [pdf, other]

Title: On Scaling Contrastive Representations for Low-Resource Speech Recognition

Authors: Lasse Borgholt, Tycho Max Sylvester Tax, Jakob Drachmann Havtorn, Lars Maaløe, Christian Igel

Comments: {\copyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[8]  arXiv:2102.01106 [pdf, other]

Title: Universal Neural Vocoding with Parallel WaveNet

Authors: Yunlong Jiao, Adam Gabrys, Georgi Tinchev, Bartosz Putrycz, Daniel Korzekwa, Viacheslav Klimkov

Comments: 5 pages, 2 figures. Accepted to ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)

[9]  arXiv:2102.01326 [pdf, other]

Title: Multimodal Attention Fusion for Target Speaker Extraction

Authors: Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Shoko Araki

Comments: 7 pages, 5 figures

Journal-ref: in IEEE Spoken Language Technology Workshop (SLT), 2021, pp. 778-784

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[10]  arXiv:2102.01363 [pdf, other]

Title: The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap

Authors: Shota Horiguchi, Nelson Yalta, Paola Garcia, Yuki Takashima, Yawen Xue, Desh Raj, Zili Huang, Yusuke Fujita, Shinji Watanabe, Sanjeev Khudanpur

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)

[11]  arXiv:2102.01380 [pdf, ps, other]

Title: Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition

Authors: Zhong Meng, Naoyuki Kanda, Yashesh Gaur, Sarangarajan Parthasarathy, Eric Sun, Liang Lu, Xie Chen, Jinyu Li, Yifan Gong

Comments: 5 pages, ICASSP 2021

Journal-ref: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada

Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD)

[12]  arXiv:2102.01746 [pdf, other]

Title: Inference of the Selective Auditory Attention using Sequential LMMSE Estimation

Authors: Ivine Kuruvila, Kubilay Can Demir, Eghart Fischer, Ulrich Hoppe

Comments: 12 pages, 13 figures

Subjects: Audio and Speech Processing (eess.AS); Signal Processing (eess.SP)

[13]  arXiv:2102.01931 [pdf, other]

Title: A Global-local Attention Framework for Weakly Labelled Audio Tagging

Authors: Helin Wang, Yuexian Zou, Wenwu Wang

Comments: Accepted to ICASSP2021

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[14]  arXiv:2102.02599 [pdf, other]

Title: VSEGAN: Visual Speech Enhancement Generative Adversarial Network

Authors: Xinmeng Xu, Yang Wang, Dongxiang Xu, Yiyuan Peng, Cong Zhang, Jie Jia, Binbin Chen

Comments: Accepted by ICASSP 2022

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD); Image and Video Processing (eess.IV)

[15]  arXiv:2102.02909 [pdf, ps, other]

Title: Infant Cry Classification with Graph Convolutional Networks

Authors: Chunyan Ji, Ming Chen, Bin Li, Yi Pan

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[16]  arXiv:2102.02998 [pdf, other]

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

Authors: Hangting Chen, Yang Yi, Dang Feng, Pengyuan Zhang

Comments: Submitted to Inerspeech 2022

Subjects: Audio and Speech Processing (eess.AS)

[17]  arXiv:2102.03109 [pdf, other]

Title: Estimation of Microphone Clusters in Acoustic Sensor Networks using Unsupervised Federated Learning

Authors: Alexandru Nelus, Rene Glitza, Rainer Martin

Comments: Accepted at ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[18]  arXiv:2102.03166 [pdf, other]

Title: Lexical and syntactic gemination in Italian consonants -- Does a geminate Italian consonant consist of a repeated or a strengthened consonant?

Authors: Maria Gabriella Di Benedetto, Stefanie Shattuck-Hufnagel, Luca De Nardis, Sara Budoni, Javier Arango, Ian Chan, Alec DeCaprio

Comments: Under revision at The Journal of the Acoustical Society of America

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[19]  arXiv:2102.03216 [pdf, ps, other]

Title: Intermediate Loss Regularization for CTC-based Speech Recognition

Authors: Jaesong Lee, Shinji Watanabe

Comments: Accepted at ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)

[20]  arXiv:2102.03468 [pdf, other]

Title: Sound Event Detection in Urban Audio With Single and Multi-Rate PCEN

Authors: Christopher Ick, Brian McFee

Comments: 5 pages, 2 figures, 1 table, accepted for publication in IEEE ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[21]  arXiv:2102.03634 [pdf, other]

Title: Speaker attribution with voice profiles by graph-based semi-supervised learning

Authors: Jixuan Wang, Xiong Xiao, Jian Wu, Ranjani Ramamurthy, Frank Rudzicz, Michael Brudno

Comments: Interspeech 2020

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[22]  arXiv:2102.03649 [pdf, other]

Title: The DKU-Duke-Lenovo System Description for the Third DIHARD Speech Diarization Challenge

Authors: Weiqing Wang, Qingjian Lin, Danwei Cai, Lin Yang, Ming Li

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[23]  arXiv:2102.03762 [pdf, other]

Title: Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism

Authors: Jisi Zhang, Catalin Zorila, Rama Doddipatla, Jon Barker

Comments: Accepted for ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)

[24]  arXiv:2102.03786 [pdf, other]

Title: EMA2S: An End-to-End Multimodal Articulatory-to-Speech System

Authors: Yu-Wen Chen, Kuo-Hsuan Hung, Shang-Yi Chuang, Jonathan Sherman, Wen-Chin Huang, Xugang Lu, Yu Tsao

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Signal Processing (eess.SP)

[25]  arXiv:2102.03951 [pdf, other]

Title: End-to-End Multi-Channel Transformer for Speech Recognition

Authors: Feng-Ju Chang, Martin Radfar, Athanasios Mouchtaris, Brian King, Siegfried Kunzmann

Comments: Accepted by 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL); Sound (cs.SD)

[26]  arXiv:2102.04029 [pdf, ps, other]

Title: Non-linear frequency warping using constant-Q transformation for speech emotion recognition

Authors: Premjeet Singh, Goutam Saha, Md Sahidullah

Comments: Accepted for publication in 2021 IEEE International Conference on Computer Communication and Informatics (IEEE ICCCI 2021)

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Signal Processing (eess.SP)

[27]  arXiv:2102.04144 [pdf, ps, other]

Title: Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement

Authors: Mostafa Sadeghi, Xavier Alameda-Pineda

Comments: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Subjects: Audio and Speech Processing (eess.AS); Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD)

[28]  arXiv:2102.04629 [pdf, other]

Title: Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform

Authors: Qinglong Li, Fei Gao, Haixin Guan, Kaichi Ma

Comments: 5 pages, 2 figures, Journal submitted

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[29]  arXiv:2102.04696 [pdf, other]

Title: Independent Vector Extraction for Fast Joint Blind Source Separation and Dereverberation

Authors: Rintaro Ikeshita, Tomohiro Nakatani

Comments: Accepted to IEEE Signal Processing Letters

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD); Signal Processing (eess.SP)

[30]  arXiv:2102.04697 [pdf, other]

Title: Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers

Authors: Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals

Comments: Accepted by ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Sound (cs.SD)

[31]  arXiv:2102.05109 [pdf, other]

Title: CDPAM: Contrastive learning for perceptual audio similarity

Authors: Pranay Manocha, Zeyu Jin, Richard Zhang, Adam Finkelstein

Comments: Dataset, code and sound examples can be found at this https URL

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[32]  arXiv:2102.05245 [pdf, other]

Title: Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

Authors: Jean-Marc Valin, Srikanth Tenneti, Karim Helwani, Umut Isik, Arvindh Krishnaswamy

Comments: Accepted for ICASSP 2021, 5 pages

Subjects: Audio and Speech Processing (eess.AS)

[33]  arXiv:2102.05259 [pdf, other]

Title: VACE-WPE: Virtual Acoustic Channel Expansion Based On Neural Networks for Weighted Prediction Error-Based Speech Dereverberation

Authors: Joon-Young Yang, Joon-Hyuk Chang

Comments: 13 pages, 12 figures, 10 tables

Subjects: Audio and Speech Processing (eess.AS)

[34]  arXiv:2102.05889 [pdf, other]

Title: ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech

Authors: Andreas Nautsch, Xin Wang, Nicholas Evans, Tomi Kinnunen, Ville Vestman, Massimiliano Todisco, Héctor Delgado, Md Sahidullah, Junichi Yamagishi, Kong Aik Lee

Journal-ref: IEEE Transactions on Biometrics, Behavior, and Identity Science 2021

Subjects: Audio and Speech Processing (eess.AS); Cryptography and Security (cs.CR); Sound (cs.SD)

[35]  arXiv:2102.06200 [pdf, other]

Title: Efficient neural networks for real-time modeling of analog dynamic range compression

Authors: Christian J. Steinmetz, Joshua D. Reiss

Comments: Updated and will appear at 152nd AES Convention (note title change)

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)

[36]  arXiv:2102.06237 [pdf, other]

Title: An Investigation of End-to-End Models for Robust Speech Recognition

Authors: Archiki Prasad, Preethi Jyothi, Rajbabu Velmurugan

Comments: Accepted to appear at ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[37]  arXiv:2102.06306 [pdf, other]

Title: DEEPF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

Authors: Satwinder Singh, Ruili Wang, Yuanhang Qiu

Comments: Accepted in ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Sound (cs.SD)

[38]  arXiv:2102.06322 [pdf, other]

Title: Joint Dereverberation and Separation with Iterative Source Steering

Authors: Taishi Nakashima, Robin Scheibler, Masahito Togami, Nobutaka Ono

Comments: 5 pages, 2 figures, accepted at ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD); Signal Processing (eess.SP)

[39]  arXiv:2102.06332 [pdf, ps, other]

Title: Data Augmentation with Signal Companding for Detection of Logical Access Attacks

Authors: Rohan Kumar Das, Jichen Yang, Haizhou Li

Comments: 5 pages, Accepted for publication in International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2021

Subjects: Audio and Speech Processing (eess.AS)

[40]  arXiv:2102.06454 [pdf, other]

Title: Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier

Authors: Guillaume Carbajal, Julius Richter, Timo Gerkmann

Journal-ref: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD)

[41]  arXiv:2102.06610 [pdf, other]

Title: Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

Authors: Jonah Casebeer, Vinjai Vale, Umut Isik, Jean-Marc Valin, Ritwik Giri, Arvindh Krishnaswamy

Comments: 5 pages, 2 figures, ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG)

[42]  arXiv:2102.06744 [pdf, ps, other]

Title: Hybrid phonetic-neural model for correction in speech recognition systems

Authors: Rafael Viana-Cámara, Mario Campos-Soberanis, Diego Campos-Sobrino

Comments: 13 pages, 3 figures, presented in COMIA 2020 (this http URL)

Subjects: Audio and Speech Processing (eess.AS); Computation and Language (cs.CL)

[43]  arXiv:2102.06816 [pdf, other]

Title: Bi-APC: Bidirectional Autoregressive Predictive Coding for Unsupervised Pre-training and Its Application to Children's ASR

Authors: Ruchao Fan, Amber Afshan, Abeer Alwan

Comments: Accepted to ICASSP2021

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG)

[44]  arXiv:2102.07047 [pdf, other]

Title: Adversarial defense for automatic speaker verification by cascaded self-supervised learning models

Authors: Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee

Comments: Accepted to ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI)

[45]  arXiv:2102.07054 [pdf, other]

Title: Inverted Vocal Tract Variables and Facial Action Units to Quantify Neuromotor Coordination in Schizophrenia

Authors: Yashish Maduwantha H.P.E.R.S, Chris Kitchen, Deanna L. Kelly, Carol Espy-Wilson

Comments: Conference

Subjects: Audio and Speech Processing (eess.AS)

[46]  arXiv:2102.07330 [pdf, other]

Title: A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement

Authors: Tyler Vuong, Yangyang Xia, Richard M. Stern

Comments: Accepted IEEE ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS)

[47]  arXiv:2102.07390 [pdf, other]

Title: Representation Learning For Speech Recognition Using Feedback Based Relevance Weighting

Authors: Purvi Agrawal, Sriram Ganapathy

Comments: arXiv admin note: substantial text overlap with arXiv:2011.00721, arXiv:2011.02136, arXiv:2001.07067

Journal-ref: IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) 2021

Subjects: Audio and Speech Processing (eess.AS)

[48]  arXiv:2102.07445 [pdf, other]

Title: On training targets for noise-robust voice activity detection

Authors: Sebastian Braun, Ivan Tashev

Journal-ref: 29th European Signal Processing Conference (EUSIPCO), 2021, Dublin, Ireland

Subjects: Audio and Speech Processing (eess.AS)

[49]  arXiv:2102.07786 [pdf, other]

Title: PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components

Authors: Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

Comments: 5 pages, accepted to ICASSP 2021

Subjects: Audio and Speech Processing (eess.AS); Machine Learning (cs.LG); Sound (cs.SD); Signal Processing (eess.SP)

[50]  arXiv:2102.07955 [pdf, other]

Title: Deep Learning based Multi-Source Localization with Source Splitting and its Effectiveness in Multi-Talker Speech Recognition

Authors: Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe, Meng Yu, Dong Yu

Comments: Submitted to Computer Speech & Language

Subjects: Audio and Speech Processing (eess.AS); Sound (cs.SD)