Audio and Speech Processing

Authors and titles for eess.AS in Dec 2023

[1]  arXiv:2312.00174 [pdf, other]

Title: Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices

Authors: Gokul Srinivasagan, Michael Deisher, Munir Georges

Comments: 5 pages, 2 figures, 2 tables, presented at the 15th ITG Conference on Speech Communications, September 2023, Aachen

Subjects: Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Image and Video Processing (eess.IV)

[2]  arXiv:2312.00231 [pdf, other]

Title: Learning domain-invariant classifiers for infant cry sounds

Authors: Charles C. Onu, Hemanth K. Sheetha, Arsenii Gorin, Doina Precup

Subjects: Audio and Speech Processing (eess.AS)

[3]  arXiv:2312.00249 [pdf, other]

Title: Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities

Authors: Jinhua Liang, Xubo Liu, Wenwu Wang, Mark D. Plumbley, Huy Phan, Emmanouil Benetos

Subjects: Audio and Speech Processing (eess.AS)

[4]  arXiv:2312.00698 [pdf, other]

Title: SPIRE-SIES: A Spontaneous Indian English Speech Corpus

Authors: Abhayjeet Singh, Charu Shah, Rajashri Varadaraj, Sonakshi Chauhan, Prasanta Kumar Ghosh

Comments: 6 pages, 7 plots, 3 tables, Accepted at O-COCOSDA 2023

Subjects: Audio and Speech Processing (eess.AS)

[5]  arXiv:2312.01744 [pdf, other]

Title: SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement

Authors: Martin Strauss, Nicola Pia, Nagashree K. S. Rao, Bernd Edler

Comments: Preprint. Accepted to IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023

Subjects: Audio and Speech Processing (eess.AS)

[6]  arXiv:2312.01808 [pdf, ps, other]

Title: Head Orientation Estimation with Distributed Microphones Using Speech Radiation Patterns

Authors: Kaspar Müller, Bilgesu Çakmak, Paul Didier, Simon Doclo, Jan Østergaard, Tobias Wolff

Comments: 6 pages, submitted to 57th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2023

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

[7]  arXiv:2312.02581 [pdf, ps, other]

Title: Auralization based on multi-perspective ambisonic room impulse responses

Authors: Kaspar Müller, Franz Zotter

Comments: 18 pages, published in Acta Acustica (Open Access), datasets are available via this https URL and this https URL

Journal-ref: Acta Acustica, Volume 4, Number 6, Article Number 25, 2020

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

[8]  arXiv:2312.02683 [pdf, other]

Title: Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler

Authors: Philippe Gonzalez, Zheng-Hua Tan, Jan Østergaard, Jesper Jensen, Tommy Sonne Alstrøm, Tobias May

Comments: Accepted to ICASSP 2024

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

[9]  arXiv:2312.03034 [pdf, other]

Title: Distributed Speech Dereverberation Using Weighted Prediction Error

Authors: Ziye Yang, Mengfei Zhang, Jie Chen

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

[10]  arXiv:2312.03129 [pdf, other]

Title: Leveraging Laryngograph Data for Robust Voicing Detection in Speech

Authors: Yixuan Zhang, Heming Wang, DeLiang Wang

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

[11]  arXiv:2312.03324 [pdf, ps, other]

Title: Lightweight Speaker Verification Using Transformation Module with Feature Partition and Fusion

Authors: Yanxiong Li, Zhongjie Jiang, Qisheng Huang, Wenchang Cao, Jialong Li

Comments: 12 pages, 5 figures, 6 tables; accepted for publication in IEEE-ACM TASLP

Subjects: Audio and Speech Processing (eess.AS)

[12]  arXiv:2312.03620 [pdf, other]

Title: Golden Gemini is All You Need: Finding the Sweet Spots for Speaker Verification

Authors: Tianchi Liu, Kong Aik Lee, Qiongqiong Wang, Haizhou Li

Comments: Accepted to IEEE/ACM Transactions on Audio, Speech, and Language Processing. Open Access: this https URL

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

[13]  arXiv:2312.03668 [pdf, other]

Title: An Integration of Pre-Trained Speech and Language Models for End-to-End Speech Recognition

Authors: Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, Kei Sawada

Comments: 6 pages, 2 figures, 3 tables, The model is available at this https URL

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

[14]  arXiv:2312.03694 [pdf, other]

Title: Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Authors: Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti, Mirco Ravanelli

Comments: The code is available at: this https URL

Subjects: Audio and Speech Processing (eess.AS)

[15]  arXiv:2312.04131 [pdf, other]

Title: Joint Training or Not: An Exploration of Pre-trained Speech Models in Audio-Visual Speaker Diarization

Authors: Huan Zhao, Li Zhang, Yue Li, Yannan Wang, Hongji Wang, Wei Rao, Qing Wang, Lei Xie

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

[16]  arXiv:2312.04324 [pdf, other]

Title: DiaPer: End-to-End Neural Diarization with Perceiver-Based Attractors

Authors: Federico Landini, Mireia Diez, Themos Stafylakis, Lukáš Burget

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

[17]  arXiv:2312.04370 [pdf, other]

Title: Investigating the Design Space of Diffusion Models for Speech Enhancement

Authors: Philippe Gonzalez, Zheng-Hua Tan, Jan Østergaard, Jesper Jensen, Tommy Sonne Alstrøm, Tobias May

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

[18]  arXiv:2312.05173 [pdf, other]

Title: Binaural multichannel blind speaker separation with a causal low-latency and low-complexity approach

Authors: Nils L. Westhausen, Bernd T. Meyer

Comments: Accepted for publication at IEEE ICASSP 2024 OJSP track

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

[19]  arXiv:2312.06065 [pdf, other]

Title: EEND-DEMUX: End-to-End Neural Speaker Diarization via Demultiplexed Speaker Embeddings

Authors: Sung Hwan Mun, Min Hyun Han, Canyeong Moon, Nam Soo Kim

Comments: Submitted to IEEE Signal Processing Letters

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

[20]  arXiv:2312.06270 [pdf, other]

Title: Testing Speech Emotion Recognition Machine Learning Models

Authors: Anna Derington, Hagen Wierstorf, Ali Özkil, Florian Eyben, Felix Burkhardt, Björn W. Schuller

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

[21]  arXiv:2312.06907 [pdf, other]

Title: w2v-SELD: A Sound Event Localization and Detection Framework for Self-Supervised Spatial Audio Pre-Training

Authors: Orlem Lima dos Santos, Karen Rosero, Roberto de Alencar Lotufo

Comments: 17 pages, 5 figures

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

[22]  arXiv:2312.07513 [pdf, other]

Title: NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection

Authors: Zexu Pan, Gordon Wichern, Francois G. Germain, Sameer Khurana, Jonathan Le Roux

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

[23]  arXiv:2312.08089 [pdf, other]

Title: Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier

Authors: Yinlin Guo, Haofan Huang, Xi Chen, He Zhao, Yuehai Wang

Comments: Accepted to ICASSP 2024. 5 pages, 1 figure

Subjects: Audio and Speech Processing (eess.AS)

[24]  arXiv:2312.08132 [pdf, ps, other]

Title: Ultra Low Complexity Deep Learning Based Noise Suppression

Authors: Shrishti Saha Shetu, Soumitro Chakrabarty, Oliver Thiergart, Edwin Mabande

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

[25]  arXiv:2312.08496 [pdf, ps, other]

Title: Metrological support of acoustic measuring installations mid-frequency devices

Authors: A.N. Grekov, N.A. Grekov, E.N. Sychev

Comments: 9 pages, 1 figure

Journal-ref: Environmental control systems. 2023. Issue. 2 (40). pp. 117-126

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

[26]  arXiv:2312.08553 [pdf, other]

Title: USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models

Authors: Shaojin Ding, David Qiu, David Rim, Yanzhang He, Oleg Rybakov, Bo Li, Rohit Prabhavalkar, Weiran Wang, Tara N. Sainath, Zhonglin Han, Jian Li, Amir Yazdanbakhsh, Shivani Agrawal

Comments: Accepted by ICASSP 2024. Preprint

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

[27]  arXiv:2312.08603 [pdf, other]

Title: NeXt-TDNN: Modernizing Multi-Scale Temporal Convolution Backbone for Speaker Verification

Authors: Hyun-Jun Heo, Ui-Hyeop Shin, Ran Lee, YoungJu Cheon, Hyung-Min Park

Comments: Accepted by ICASSP 2024

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

[28]  arXiv:2312.08610 [pdf, other]

Title: A computationally efficient semi-blind source separation based approach for nonlinear echo cancellation based on an element-wise iterative source steering

Authors: Kunxing Lu, Xianrui Wang, Tetsuya Ueda, Shoji Makino, Jingdong Chen

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

[29]  arXiv:2312.08622 [pdf, other]

Title: Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verification

Authors: Haibin Wu, Heng-Cheng Kuo, Yu Tsao, Hung-yi Lee

Comments: Submitted to 2024 ICASSP

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

[30]  arXiv:2312.08641 [pdf, other]

Title: Towards Automatic Data Augmentation for Disordered Speech Recognition

Authors: Zengrui Jin, Xurong Xie, Tianzi Wang, Mengzhe Geng, Jiajun Deng, Guinan Li, Shujie Hu, Xunying Liu

Comments: To appear at IEEE ICASSP 2024

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

[31]  arXiv:2312.08821 [pdf, other]

Title: Reconstruction of Sound Field through Diffusion Models

Authors: Federico Miotello, Luca Comanducci, Mirco Pezzoli, Alberto Bernardini, Fabio Antonacci, Augusto Sarti

Comments: Accepted for publication at ICASSP 2024

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

[32]  arXiv:2312.08856 [pdf, other]

Title: Attention-Guided Adaptation for Code-Switching Speech Recognition

Authors: Bobbi Aditya, Mahdin Rohmatillah, Liang-Hsuan Tai, Jen-Tzung Chien

Comments: Accepted to ICASSP 2024

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

[33]  arXiv:2312.08908 [pdf, other]

Title: Multi-Microphone Noise Data Augmentation for DNN-based Own Voice Reconstruction for Hearables in Noisy Environments

Authors: Mattes Ohlenbusch, Christian Rollwage, Simon Doclo

Comments: ICASSP 2024 (c) 2024 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)

[34]  arXiv:2312.08998 [pdf, ps, other]

Title: Design, construction and evaluation of emotional multimodal pathological speech database

Authors: Ting Zhu, Shufei Duan, Huizhi Liang, Wei Zhang

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

[35]  arXiv:2312.09034 [pdf, other]

Title: Fusion of Audio and Visual Embeddings for Sound Event Localization and Detection

Authors: Davide Berghi, Peipei Wu, Jinzheng Zhao, Wenwu Wang, Philip J. B. Jackson

Comments: ICASSP 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

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

[36]  arXiv:2312.09100 [pdf, other]

Title: FastInject: Injecting Unpaired Text Data into CTC-based ASR training

Authors: Keqi Deng, Philip C. Woodland

Comments: Accepted by ICASSP2024

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

[37]  arXiv:2312.09572 [pdf, other]

Title: IR-UWB Radar-Based Contactless Silent Speech Recognition of Vowels, Consonants, Words, and Phrases

Authors: Sunghwa Lee, Younghoon Shin, Myungjong Kim, Jiwon Seo

Comments: Submitted to IEEE Access

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

[38]  arXiv:2312.09578 [pdf, ps, other]

Title: Self-Supervised Learning for Anomalous Sound Detection

Authors: Kevin Wilkinghoff

Comments: Accepted for presentation at IEEE ICASSP 2024

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

[39]  arXiv:2312.09620 [pdf, other]

Title: A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder

Authors: Yang Xiang, Jingguang Tian, Xinhui Hu, Xinkang Xu, ZhaoHui Yin

Comments: Accepted by ICASSP 2024

Subjects: Audio and Speech Processing (eess.AS)

[40]  arXiv:2312.09645 [pdf, other]

Title: Fine-Tuned Self-Supervised Speech Representations for Language Diarization in Multilingual Code-Switched Speech

Authors: Geoffrey Frost, Emily Morris, Joshua Jansen van Vüren, Thomas Niesler

Comments: Presented at SACAIR 2022

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

[41]  arXiv:2312.09663 [pdf, other]

Title: Toward Deep Drum Source Separation

Authors: Alessandro Ilic Mezza, Riccardo Giampiccolo, Alberto Bernardini, Augusto Sarti

Comments: 9 pages, 2 figures, 3 tables. Published in Pattern Recognition Letters, 2024

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

[42]  arXiv:2312.09747 [pdf, other]

Title: SELM: Speech Enhancement Using Discrete Tokens and Language Models

Authors: Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv, Ning Jiang, Guoqing Zhao, Lei Xie

Comments: Accepted by ICASSP 2024

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

[43]  arXiv:2312.09760 [pdf, other]

Title: U2-KWS: Unified Two-pass Open-vocabulary Keyword Spotting with Keyword Bias

Authors: Ao Zhang, Pan Zhou, Kaixun Huang, Yong Zou, Ming Liu, Lei Xie

Comments: Accepted by ASRU2023

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

[44]  arXiv:2312.09768 [pdf, other]

Title: Decoding Envelope and Frequency-Following EEG Responses to Continuous Speech Using Deep Neural Networks

Authors: Mike Thornton, Danilo Mandic, Tobias Reichenbach

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

[45]  arXiv:2312.09952 [pdf, other]

Title: Multi-level graph learning for audio event classification and human-perceived annoyance rating prediction

Authors: Yuanbo Hou, Qiaoqiao Ren, Siyang Song, Yuxin Song, Wenwu Wang, Dick Botteldooren

Comments: Accepted by ICASSP 2024

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

[46]  arXiv:2312.10087 [pdf, ps, other]

Title: Revisiting the Entropy Semiring for Neural Speech Recognition

Authors: Oscar Chang, Dongseong Hwang, Olivier Siohan

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

[47]  arXiv:2312.10088 [pdf, ps, other]

Title: On Robustness to Missing Video for Audiovisual Speech Recognition

Authors: Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan

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

[48]  arXiv:2312.10687 [pdf, other]

Title: MM-TTS: Multi-modal Prompt based Style Transfer for Expressive Text-to-Speech Synthesis

Authors: Wenhao Guan, Yishuang Li, Tao Li, Hukai Huang, Feng Wang, Jiayan Lin, Lingyan Huang, Lin Li, Qingyang Hong

Comments: Accepted at AAAI2024

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

[49]  arXiv:2312.10741 [pdf, other]

Title: StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis

Authors: Yu Zhang, Rongjie Huang, Ruiqi Li, JinZheng He, Yan Xia, Feiyang Chen, Xinyu Duan, Baoxing Huai, Zhou Zhao

Comments: Accepted by AAAI 2024

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

[50]  arXiv:2312.10756 [pdf, other]

Title: Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios

Authors: Yuzhu Wang, Archontis Politis, Tuomas Virtanen

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