Skip to content
conftrace_

Interspeech 2025

1,179 papers

Voice Conversion for Likability Control via Automated Rating of Speech Synthesis Corpora

Hitoshi Suda, Shinnosuke Takamichi, Satoru Fukayama

Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion

Seymanur Akti, Tuan-Nam Nguyen, Alexander Waibel

Evaluating Speech Enhancement Performance Across Demographics and Language

José Giraldo, Alex Peiró-Lilja, Carme Armentano-Oller, Rodolfo Zevallos, Cristina España-Bonet

On the Language and Gender Biases in PSTN, VoIP and Neural Audio Codecs

Kemal Altwlkany, Amar Kuric, Emanuel Lacic

FaiST: A Benchmark Dataset for Fairness in Speech Technology

Maliha Jahan, Yinglun Sun, Priyam Mazumdar, Zsuzsanna Fagyal, Thomas Thebaud

The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages

Chris Emezue, The NaijaVoices Community, Busayo Awobade, Abraham Toluwase Owodunni, Handel Emezue

Unified Microphone Conversion: Many-to-Many Device Mapping via Feature-wise Linear Modulation

Myeonghoon Ryu, Hongseok Oh, Suji Lee, Han Park

Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification

Emiliano Acevedo, Martín Rocamora, Magdalena Fuentes

Beyond Conventional Metrics: using Entropic Triangles to Explain Balancing Methods in Acoustic Scene Classification

Claudia Montero-Ramírez, Alba Martínez-Serrano, Jorge Garcelán-Gómez, Francisco J. Valverde-Albacete, Carmen Peláez-Moreno

Fully Few-shot Class-incremental Audio Classification Using Multi-level Embedding Extractor and Ridge Regression Classifier

Yongjie Si, Yanxiong Li, Jiaxin Tan, Qianhua He, Il-Youp Kwak

Multi-view Fusion and Parameter Perturbation for Few-Shot Class-Incremental Audio Classification

Yulu Fang, Mingyue He, Qisheng Xu, Jianqiao Zhao, Cheng Yang

Training Onset-and-Offset-Aware Sound Event Detection on a Heterogeneous Dataset via Probabilistic Sequential Modeling

Tomoya Yoshinaga, Yoshiaki Bando, Keitaro Tanaka, Keisuke Imoto, Masaki Onishi

Creaky Voice Facilitates More Efficient Phonological Processing of Mandarin Tone 3

Zixia Fan, Ronny Ibrahim, Joshua Penney, Felicity Cox

Characterization of voice cue sensitivity and vocal emotion recognition across the adult lifespan

Laura Rachman, Deniz Başkent

Language and Accent Familiarity Effects on the Use of Acoustic Cues in Talker Identification

Shengyue Xiong, Zhe-chen Guo, Bharath Chandrasekaran

Prediction of listening effort ratings for habitual and clear-Lombard speech presented in noise

Esther Janse, Chen Shen, Martin Cooke

Speech stimulus design to study the neural coding of speech and the impact of cochlear synaptopathy

Etienne Gaudrain, Sarah Verhulst, Deniz Başkent

Multitalker Babble in English Vowel Perception Training: A Comparison between Humans and Neural Models

Wenwei Dong, Alif Silpachai, Catia Cucchiarini, Helmer Strik

Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control

Yunkee Chae, Eunsik Shin, Suntae Hwang, Seungryeol Paik, Kyogu Lee

Simple and Effective Content Encoder for Singing Voice Conversion via SSL-Embedding Dimension Reduction

Wangjin Zhou, Tianjiao Du, Chenglin Xu, Sheng Li, Yi Zhao

DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching

Wei Chen, Binzhu Sha, Dan Luo, Jing Yang, Zhuo Wang

VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schrödinger Bridge

Zijing Zhao, Kai Wang, Hao Huang, Ying Hu, Liang He

Neurodyne: Neural Pitch Manipulation with Representation Learning and Cycle-Consistency GAN

Yicheng Gu, Chaoren Wang, Zhizheng Wu, Lauri Juvela

Bridging Speech and Singing: Multi-stage Speech-Prompted Singing Voice Conversion with Speaker Embedding Adaptation

Mingda Liu, Jiatong Shi

Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation

Mu Yang, Bowen Shi, Matthew Le, Wei-Ning Hsu, Andros Tjandra

TVC-MusicGen: Time-Varying Structure Control for Background Music Generation via Self-Supervised Training

Chenyu Yang, Hangting Chen, Shuai Wang, Haina Zhu, Haizhou Li

VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion

Joon-Seung Choi, Dong-Min Byun, Hyung-Seok Oh, Seong-Whan Lee

Towards Early Prediction of Self-Supervised Speech Model Performance

Ryan Whetten, Lucas Maison, Titouan Parcollet, Marco Dinarelli, Yannick Estève

Differentiable K-means for Fully-optimized Discrete Token-based ASR

Kentaro Onda, Yosuke Kashiwagi, Emiru Tsunoo, Hayato Futami, Shinji Watanabe

DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective

Hyung-gun Chi, Zakaria Aldeneh, Tatiana Likhomanenko, Oggi Rudovic, Takuya Higuchi

GigaAM: Efficient Self-Supervised Learner for Speech Recognition

Aleksandr Kutsakov, Alexandr Maximenko, Georgii Gospodinov, Pavel Bogomolov, Fyodor Minkin

Self-supervised learning of speech representations with Dutch archival data

Nik Vaessen, Roeland Ordelman, David A. van Leeuwen

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR

Mingyu Cui, Yifan Yang, Jiajun Deng, Jiawen Kang, Shujie Hu

Speech Enhancement with Dual-path Multi-Channel Linear Prediction Filter and Multi-norm Beamforming

Chengyuan Qin, Wenmeng Xiong, Jing Zhou, Maoshen Jia, Changchun Bao

A Three-Stage Beamforming with Harmonic Guidance for Multi-Channel Speech Enhancement

Nurali Alip, Tianrui Wang, Rui Cao, Meng Ge, Jingru Lin

WTFormer: A Wavelet Conformer Network for MIMO Speech Enhancement with Spatial Cues Peservation

Lu Han, Junqi Zhao, Renhua Peng

ARiSE: Auto-Regressive Multi-Channel Speech Enhancement

Pengjie Shen, Xueliang Zhang, Zhong-Qiu Wang

A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions

Zheng Wang, Xiaobin Rong, Yu Sun, Tianchi Sun, Zhibin Lin

Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement

Yujie Yang, Bing Yang, Xiaofei Li

Open Universal Arabic ASR Leaderboard

Yingzhi Wang, Anas Alhmoud, Muhammad Alqurishi

VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining

Jianheng Zhuo, Yifan Yang, Yiwen Shao, Yong Xu, Dong Yu

Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning

Ömer Tarik Özyilmaz, Matt Coler, Matias Valdenegro-Toro

Leveraging Geographic Metadata for Dialect-Aware Speech Recognition

Pouya Mehralian, Hugo Van hamme

Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR

Zheng Xin Yong, Vineel Pratap, Michael Auli, Jean Maillard

Mixture of LoRA Experts for Low-Resourced Multi-Accent Automatic Speech Recognition

Raphaël Bagat, Irina Illina, Emmanuel Vincent

Efficient Multilingual ASR Finetuning via LoRA Language Experts

Jiahong Li, Yiwen Shao, Jianheng Zhuo, Chenda Li, Liliang Tang

Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR

Hongli Yang, Sheng Li, Hao Huang, Ayiduosi Tuohan, Yizhou Peng

Switch Conformer with Universal Phonetic Experts for Multilingual ASR

Masato Mimura, Jaeyoung Lee, Tatsuya Kawahara

Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing

Jin Li, Man-Wai Mak, Johan Rohdin, Kong Aik Lee, Hynek Hermansky

Towards Robust Speaker Recognition against Intrinsic Variation with Foundation Model Few-shot Tuning and Effective Speech Synthesis

Zhiyong Chen, Shuhang Wu, Xinnuo Li, Zhiqi Ai, Shugong Xu

Evaluating Deep Speaker Embedding Robustness to Domain, Sampling Rate, and Codec Variations

Alexandre Ferro Filho, Diogo Fernandes Costa Silva, Pedro Elias Engelberg Silva Borges, Arlindo Rodrigues Galvão Filho

Disentangling Speaker and Content in Pre-trained Speech Models with Latent Diffusion for Robust Speaker Verification

Zhe Li, Man-Wai Mak, Jen-Tzung Chien, Mert Pilanci, Zezhong Jin

ParaNoise-SV: Integrated Approach for Noise-Robust Speaker Verification with Parallel Joint Learning of Speech Enhancement and Noise Extraction

Minu Kim, Kangwook Jang, Hoirin Kim

SSPS: Self-Supervised Positive Sampling for Robust Self-Supervised Speaker Verification

Theo Lepage, Reda Dehak

``Dyadosyncrasy'', Idiosyncrasy and Demographic Factors in Turn-Taking

Julio Cesar Cavalcanti, Gabriel Skantze

Does effortful speech production indicate communication difficulty caused by noise and hearing aid support?

Lena-Marie Huttner, Jeppe H. Christensen, Gitte Keidser, Tobias May, Torsten Dau

Rapport-Building Dialogue Strategies for Deeper Connection: Integrating Proactive Behavior, Personalization, and Aizuchi Backchannels

Muhammad Yeza Baihaqi, Angel Garcia Contreras, Seiya Kawano, Koichiro Yoshino

Backchannel prediction for natural spoken dialog systems using general speaker and listener information

Yoshinori Fukunaga, Ryota Nishimura, Kengo Ohta, Norihide Kitaoka

Visual Cues Support Robust Turn-taking Prediction in Noise

Sam O'Connor Russell, Naomi Harte

Gaze-Enhanced Multimodal Turn-Taking Prediction in Triadic Conversations

Seongsil Heo, Christi Miller, Calvin Murdock, Michael Proulx

Exploratory Analysis of Brainstem fMRI Data During Sustained Phonation

Carey Smith, Hu Cheng, Pertti Palo, Daniel Aalto, Steven M. Lulich

A real-time MRI study on asymmetry in velum dynamics during VCV production with nasal sounds

Chetan Sharma, Vaishnavi Chandwanshi, Shreya Shrikant Karkun, Aditya Anand Gupta, Prasanta Kumar Ghosh

Overestimated performance of auditory attention decoding caused by experimental design in EEG recordings

Yujie Yan, Xiran Xu, Haolin Zhu, Songyi Li, Bo Wang

SSF-DST: A Spectro-Spatial Features Enhanced Deep Spatiotemporal Network for EEG-Based Auditory Attention Detection

Tong Zhu, Xiaoke Yang, Jian Zhou, Lu Li, Zhao Lv

Decoding Speaker-Normalized Pitch from EEG for Mandarin Perception

Jia-Xin Chen, Yi-Ming Wang, Ziyu Zhang, Jiayang Han, Yin-Long Liu

Extended High-frequency Cues to Phoneme Recognition: Insights from ASR

Zhe-chen Guo, Bharath Chandrasekaran

Self-supervised Optimality-Guided Learning of Speech Articulation

Juraj Simko, Benjamin Elie, Alice Turk

Theoretical proposal for a unified Bayesian model of adaptation in non-interactive and interactive speech production

Mélen Guillaume, Anahita Basirat, Julien Diard

Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles

Miika Toikkanen, June-Woo Kim

Patient-Aware Feature Alignment for Robust Lung Sound Classification: Cohesion-Separation and Global Alignment Losses

Seung Gyu Jeong, Seong Eun Kim

Disentangling Dual-Encoder Masked Autoencoder for Respiratory Sound Classification

Peidong Wei, Shiyu Miao, Lin Li

Adaptive Differential Denoising for Respiratory Sounds Classification

Gaoyang Dong, Zhicheng Zhang, Ping Sun, Minghui Zhang

Effect of physical exercise on voice in people living with COPD

Lauren G Reinders, Loes van Bemmel, Alexander Mackay, David Nobbs, Frits M.E. Franssen

Towards Pre-training an Effective Respiratory Audio Foundation Model

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Yasunori Ohishi

Developing a LeFF Transformer Model for Exacerbated Speech Detection in COPD and Asthma

Yuyang Yan, Sami O. Simons, Visara Urovi

SPEAKtoCOPD: a flashmob study to collect COPD speech

Loes van Bemmel, Lauren G Reinders, Folkert Brijker, Bas Holverda, Frits M.E. Franssen

Co-registration of real-time MRI and respiration for speech research

Yubin Zhang, Prakash Kumar, Ye Tian, Ziwei Zhao, Xuan Shi

Reconstruction of the Complete Vocal Tract Contour Through Acoustic to Articulatory Inversion Using Real-Time MRI Data

Sofiane Azzouz, Pierre-André Vuissoz, Yves Laprie

2D Immersed Boundary Method in Vocal Tract Acoustics: An Eulerian–Lagrangian Model for Simulation of Diphthongs

Rongshuai Wu, Debasish Ray Mohapatra, Sidney Fels

Constrained LDDMM for Dynamic Vocal Tract Morphing: Integrating Volumetric and Real-Time MRI

Tharinda Piyadasa, Joan Glaunès, Amelia Gully, Michael Proctor, Kirrie Ballard

How sibilant spectra shape gender perception in prepubertal children: A voice morphing study

Riccarda Funk, Melanie Weirich, Adrian Simpson

The Role of Voiced Consonant Duration in Sung Vowel-Consonant and Consonant-Vowel Recognition

Allan Vurma, Einar Meister, Lya Meister, Jaan Ross, Marju Raju

Articulatory modeling of the S-shaped F2 trajectories observed in Öhman's spectrographic analysis of VCV syllables

Frédéric Berthommier

TF-Mamba: A Time-Frequency Network for Sound Source Localization

Yang Xiao, Rohan Kumar Das

SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction

Tuochao Chen, D Shin, Hakan Erdogan, Sinan Hersek

AuralNet: Hierarchical Attention-based 3D Binaural Localization of Overlapping Speakers

Linya Fu, Yu Liu, Zhijie Liu, Zedong Yang, Zhong-Qiu Wang

Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses

Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Jonathan Le Roux

Effect of Noise Floor in Room Impulse Response on Speech Perception Under Spherical Harmonics-based Spatial Sound Reproduction

Yunqi C. Zhang, Dhruv Jagmohan, Hong Kit Li, C. T. Justine Hui, Yusuke Hioka

Temporal Modeling of Room Impulse Response Generation via Multi-Scale Autoregressive Learning

Sheng Lyu, Yuemin Yu, Chenshu Wu

NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data

Tahir Javed, Kaushal Bhogale, Mitesh M. Khapra

A Multi-Dialectal Dataset for German Dialect ASR and Dialect-to-Standard Speech Translation

Verena Blaschke, Miriam Winkler, Constantin Förster, Gabriele Wenger-Glemser, Barbara Plank

Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation

Chenyang Le, Yinfeng Xia, Huiyan Li, Manhong Wang, Yutao Sun

Multilingual Query-by-Example KWS for Indian Languages using Transliteration

Kirandevraj R, Vinod K Kurmi, Vinay Namboodiri, CV Jawahar

Scaling pseudo-labeling data for end-to-end low-resource speech translation (the case of Kurdish language)

Mohammad Mohammadamini, Aghilas Sini, Marie Tahon, Antoine Laurent

Structured pruning for efficient systolic array accelerated cascade Speech-to-Text Translation

Jean-Luc Rouas, Charles Brazier, Leila Ben Letaifa, Rafael Medina, Pedro Palacios

Universal Speech Enhancement with Regression and Generative Mamba

Rong Chao, Rauf Nasretdinov, Yu-Chiang Frank Wang, Ante Jukić, Szu-Wei Fu

FUSE: Universal Speech Enhancement using Multi‐Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge

Nabarun Goswami, Tatsuya Harada

DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration

Sanberk Serbest, Tijana Stojkovic, Milos Cernak, Andrew Harper

Scaling beyond Denoising: Submitted System and Findings in URGENT Challenge 2025

Zhihang Sun, Andong Li, Tong Lei, Rilin Chen, Meng Yu

Multistage Universal Speech Enhancement System for URGENT Challenge

Xiaohuai Le, Zhuangqi Chen, Siyu Sun, Xianjun Xia, Chuanzeng Huang