Interspeech 2025

1,179 papers

MelRe: Vision-Based Mel-Spectrogram Restoration

Kaixuan Luan, Xiaoda Yang, Shile Cai, Ruofan Hu, Minghui Fang

Unified Variational and Physics-aware Model for Room Impulse Response Estimation

Louis Lalay, Mathieu Fontaine, Roland Badeau

Boosting StoRM Convergence with Metric Guidance and Non-uniform State-Sampling for Optimal Dereverberation

Chandra Mohan Sharma, Arnab Kumar Roy, Anupam Mandal, Prasanta Kumar Ghosh, Prasanna Kumar Kr

Bilingual Speakers Exhibit Cognitive Fatigue: A Speech Disfluencies Case Study on Research Talks

Ashwin Ram, Marisol Muñoz, Zoi Gkalitsiou, Alexandros G. Dimakis

Sentence-Final Particles in Mandarin Child-Directed Speech: Frequency and Impact on Speech Rate

Yizhi Liu, Luyuan Geng, Yan Gu, Mengru Han

The Effect of Word Predictability on Spoken Cross-Language Intelligibility

Wei Xue, Iuliia Zaitova, Bernd Möbius

A Gradient Effect of Hand Beat Timing on Spoken Word Recognition

Chengjia Ye, James M. McQueen, Hans Rutger Bosker

Processing of grammatical information in cochlear implant simulated speech by German adult listeners

Atty Schouwenaars, Esther Ruigendijk

LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios

Yifan Liang, Kang Yang, Fangkun Liu, Andong Li, Xiaodong Li

VisualSpeech: Enhancing Prosody Modeling in TTS Using Video

Shumin Que, Anton Ragni

Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis

Minsu Kim, Pingchuan Ma, Honglie Chen, Stavros Petridis, Maja Pantic

Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation

Fang Kang, Yin Cao, Haoyu Chen

Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation

Hyung Kyu Kim, Hak Gu Kim

MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing

Junjie Zheng, Zihao Chen, Chaofan Ding, Yunming Liang, Yihan Fan

J-j-j-just Stutter: Benchmarking Whisper's Performance Disparities on Different Stuttering Patterns

Charan Sridhar, Shaomei Wu

Development and Validation of a Wav2Vec 2.0-Based Cross-Language Methodology for Measurement of Articulatory Precision

Tanya Talkar, Kan Kawabata, Connor Higgins, Sean Tobyne

Multimodal Assessment of Speech Impairment in Amyotrophic Lateral Sclerosis Using Audio-Visual and Machine Learning Approaches

Francesco Pierotti, Andrea Bandini

Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers

Terry Yi Zhong, Esther Janse, Cristian Tejedor-García, Louis ten Bosch, Martha Larson

Relationship between objective and subjective perceptual measures of speech in individuals with head and neck cancer

Bence Mark Halpern, Thomas Tienkamp, Teja Rebernik, Rob J.J.H. van Son, Martijn Wieling

Anne Hermes, Ivana Didirková, Philipp Buech, Gilles Vannuscorps

A Copula-Based Generative Score-Level Fusion Model for Speaker Verification

Sandro Cumani

SEED: Speaker Embedding Enhancement Diffusion Model

Kihyun Nam, Jungwoo Heo, Jee-weon Jung, Gangin Park, Chaeyoung Jung

Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification

Jin Sob Kim, Hyun Joon Park, WooSeok Shin, Sung Won Han

ATMM-SAGA: Alternating Training for Multi-Module with Score-Aware Gated Attention SASV system

Amro Asali, Yehuda Ben-Shimol, Itshak Lapidot

MASV: Speaker Verification with Global and Local Context Mamba

Yang Liu, Li Wan, Yiteng Huang, Ming Sun, Xinhao Mei

Clustering-based Hard Negative Sampling for Supervised Contrastive Speaker Verification

Piotr Masztalski, Michał Romaniuk, Jakub Żak, Mateusz Matuszewski, Konrad Kowalczyk

A Domain Robust Pre-Training Method with Local Prototypes for Speaker Verification

Qing Gu, Yan Song, Haoyu Song, Nan Jiang, Lirong Dai

Pushing the Frontiers of Self-Distillation Prototypes Network with Dimension Regularization and Score Normalization

Yafeng Chen, Chong Deng, Hui Wang, Yiheng Jiang, Han Yin

Boundary-Conscious Pruning: Hard Set-Aware Model Compression for Efficient Speaker Recognition

Seongkyu Mun, Jubum Han

From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data

Ahmed Attia, Dorottya Demszky, Jing Liu, Carol Espy-Wilson

Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction

Christophe Van Gysel, Maggie Wu, Lyan Verwimp, Caglar Tirkaz, Marco Bertola

Voice Activity-based Text Segmentation for ASR Text Denormalization

Sashi Novitasari, Takashi Fukuda, Gakuto Kurata

Semi-Supervised Learning for Automatic Speech Recognition with Word Error Rate Estimation and Targeted Domain Data Selection

Chanho Park, Thomas Hain

ASR Confidence Estimation using True Class Lexical Similarity Score

Nagarathna Ravi, Thishyan Raj T, Ravi Teja Chaganti, Vipul Arora

LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context

Natsuo Yamashita, Masaaki Yamamoto, Hiroaki Kokubo, Yohei Kawaguchi

VoxAging: Continuously Tracking Speaker Aging with a Large-Scale Longitudinal Dataset in English and Mandarin

Zhiqi Ai, Meixuan Bao, Zhiyong Chen, Zhi Yang, Xinnuo Li

Do you read me? - flow of speech effect on speaker recognition systems

Alicja Martinek, Joanna Gajewska, Ewelina Bartuzi-Trokielewicz

Using gender, phonation and age to interpret automatically discovered speech attributes for explainable speaker recognition

Carole Millot, Clara Ponchard, Cedric Gendrot, Jean-Francois Bonastre, Orane Dufour

Universal Semantic Disentangled Privacy-preserving Speech Representation Learning

Biel Tura-Vecino, Subhadeep Maji, Aravind Varier, Antonio Bonafonte, Ivan Valles

SCD-Conformer: Semantic Content Disentanglement for Text-Independent Speaker Verification

Shanshan Yao, Dianlong Liu, Tian Li

LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention

Aditya Srinivas Menon, Raj Prakash Gohil, Kumud Tripathi, Pankaj Wasnik

Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering

Andrés Carofilis, Pradeep Rangappa, Srikanth Madikeri, Shashi Kumar, Sergio Burdisso

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models

Abdul Hannan, Alessio Brutti, Shah Nawaz, Mubashir Noman

Knowledge Distillation Method for Pruned RNN-T Models via Pruning Bounds Sharing and Losses Confusion

Xiaocan Zhang, Weiwei Jiang, Guibin Zheng, Chenhao Jing, Jiqing Han

Dynamic Acoustic Model Architecture Optimization in Training for ASR

Jingjing Xu, Zijian Yang, Albert Zeyer, Eugen Beck, Ralf Schlüter

Towards Efficiently Whisper Fine-tuning with Monotonic Alignments

Ziyang Zhuang, Tao Wei, Ming Fang, Ning Cheng, Shaojun Wang

Thinking Fast and Slow: Robust Speech Recognition via Deep Filter-Tuning

Dianwen Ng, Kun Zhou, Bin Ma, Eng Siong Chng

Attention-Free Dual-Mode ASR with Latency-Controlled Selective State Spaces

Takafumi Moriya, Masato Mimura, Kiyoaki Matsui, Hiroshi Sato, Kohei Matsuura

Exploring Linear Variant Transformers and k-NN Memory Inference for Long-Form ASR

Carlos Carvalho, Jinchuan Tian, William Chen, Yifan Peng, Alberto Abad

Improving Generalization of End-to-End ASR through Diversity and Independence Regularization

Ye-Eun Ko, Mun-Hak Lee, Dong-Hyun Kim, Joon-Hyuk Chang

SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment

SooHwan Eom, Mark Hasegawa-Johnson, Chang D. Yoo

Fine-Tuning ASR for Stuttered Speech: Personalized vs. Generalized Approaches

Dena Mujtaba, Nihar R. Mahapatra

Hybrid HMM-SVM classifier using frication-based features for detection of non-normative sibilant articulation patterns in Polish children’s speech

Zuzanna Miodonska

Articulatory clarity and variability before and after surgery for tongue cancer

Thomas Tienkamp, Fleur van Ast, Roos van der Veen, Teja Rebernik, Raoul Buurke

Phonetic Posteriorgram-Based Phoneme Selection for Vocal Cord Disorder Classification in Continuous Mandarin Speech

Chih-Ning Chen, Yu-Lan Chuang, Ming-Jhang Yang, Wei-Cheng Hsu, Yung-An Tsou

MVP: Multi-source Voice Pathology detection

Alkis Koudounas, Moreno La Quatra, Gabriele Ciravegna, Marco Fantini, Erika Crosetti

Hybrid Expert Knowledge and Self-Supervised Learning for Diagnostic Modeling of Adductor Spasmodic and Primary Myotonic Dysphonia

Zhou Du, Hang Chen, Huijun Ding, Jun Du, Zhen Chen

GenECA: A General-Purpose Framework for Real-Time Adaptive Multimodal Embodied Conversational Agents

Santosh Patapati, Aashrith Tatineni, Trisanth Srinivasan

Simultaneous Speech Translation Integrated Compact Multiple Sound Spot Synthesis System On A Laptop Carried Out With A Backpack

Takuma Okamoto, Michiyo Kono

Rollback Speech: Smart Feedback Prompts for Lost Utterances in Unstable Online Calls

Yuni Amaloa Quintero Villalobos, Wafaa Wardah, Sebastian Möller, Robert P. Spang

TargetVoice: Single Channel Low-Latency Target Speaker Extraction

Arun Kumar Pallala, Nivedita Chennupati, Balaji Padmanaban, Rakesh Pogula, Uma Subhashini Ravuri

Co-Speech Motion for Virtual Agents in Dialogue Using LLM-Driven Primitive Action Selection

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

Real-Time Diffusion Buffer for Speech Enhancement On A Laptop

Bunlong Lay, Rostilav Makarov, Timo Gerkmann

Real-time TSE demonstration via SoundBeam with KD

Keigo Wakayama, Tomoko Kawase, Takafumi Moriya, Marc Delcroix, Hiroshi Sato

AxLSTMs: learning self-supervised audio representations with xLSTMs

Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan

EnCodecMAE: leveraging neural codecs for universal audio representation learning

Leonardo Pepino, Pablo Riera, Luciana Ferrer

Factorized RVQ-GAN For Disentangled Speech Tokenization

Sameer Khurana, Dominik Klement, Antoine Laurent, Dominik Boboš, Juraj Novosad

PAST: Phonetic-Acoustic Speech Tokenizer

Nadav Har-Tuv, Or Tal, Yossi Adi

Articulatory Strategy in Vowel Production as a Basis for Speaker Discrimination

Justin J. H. Lo, Patrycja Strycharczuk, Sam Kirkham

Rhotic Articulation in Australian English: Insights from MRI

Michael Proctor, Tünde Szalay, Tharinda Piyadasa, Craig Jin, Naeim Sanaei

Articulatory variations in Apical Vowels in Southwestern Mandarin

Jing Huang, Feng-fan Hsieh, Yueh-chin Chang

Lateral Channel Formation in Australian English /l/: Insights from Magnetic Resonance Imaging

Tünde Szalay, Michael Proctor, Amelia Gully, Tharinda Piyadasa, Craig Jin

Supralaryngeal Kinematics of Implosives in Central Vietnamese: An EMA Study

Paul McGuire, Kye Shibata, Thanh Viet Cao, Feng-fan Hsieh, Yueh-chin Chang

Influence of wall coverings of 3D-printed vocal tract models on measured transfer functions

Peter Birkholz, Dominik Schäfer, Patrick Häsner, Jihyeon Yun, Iris Kruppke

Speech Kinematic Analysis from Acoustics: Scientific, Clinical and Practical Applications

Carol Espy-Wilson

A Watermark for Auto-Regressive Speech Generation Models

Yihan Wu, Ruibo Chen, Georgios Milis, Junfeng Guo, Heng Huang

VoiceNoNG: Robust High-Quality Speech Editing Model without Hallucinations

Sung-Feng Huang, Heng-Cheng Kuo, Zhehuai Chen, Xuesong Yang, Pin-Jui Ku

SpeechSEC: A Unified Multi-Task Framework for Speech Synthesis, Editing, and Continuation

Liming Liang, Dongchao Yang, Xianwei Zhuang, Yuxin Xie, Luo Chen

Accelerating Diffusion-based Text-to-Speech Model Trainingwith Dual Modality Alignment

Jeongsoo Choi, Zhikang Niu, Ji-Hoon Kim, Chunhui Wang, Joon Son Chung

Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback

Jingyi Chen, Ju Seung Byun, Micha Elsner, Pichao WANG, Andrew Perrault

Efficient Neural and Numerical Methods for High-QualityOnline Speech Spectrogram Inversion via Gradient Theorem

Andrés Fernández, Juan Azcarreta Ortiz, Cagdas Bilen, Jesus Monge Alvarez

On the Design of a Robust Superdirective Beamformer and Topology Parameter Optimization with Frustum-Shaped Microphone Arrays Featuring Multiple Rings

Kunlong Zhao, Gongping Huang, Xudong Zhao, Jingdong Chen, Jacob Benesty

Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform

Xiangzhu Kong, Hao Huang, Zhijian Ou

Attention Models and Auditory Transduction Features for Noise Robustness

Cathal Ó Faoláin, Andrew Hines

EmbedAug: An Augmentation Scheme for End-to-End Automatic Speech Recognition

Ashish Panda, Sunil Kumar Kopparapu

MOVER: Combining Multiple Meeting Recognition Systems

Naoyuki Kamo, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani

HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization

Hyebin Ahn, Kangwook Jang, Hoirin Kim

Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down

Yingzhi Wang, Anas Alhmoud, Saad Alsahly, Muhammad Alqurishi, Mirco Ravanelli

Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning

Siyi Zhao, Wei Wang, Yanmin Qian

SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition

Longjie Luo, Lin Li, Qingyang Hong

StarGAN-Aug: A Cross-domain Fault Audio Generation Method for High-performance Fault Diagnosis of Power Transformers

Ben Niu, Yangjie Wei, Gang Yang, Yuqiao Wang, Shengling Yu

Acoustic Detection of UAV Abnormality Using One Ground-Based Acoustic Vector Sensor

Dengjian Zhou, Jianghan Hai, Sijia Liao, Yue Ivan Wu, Kainam Thomas Wong

Finetune Large Pre-Trained Model Based on Frequency-Wise Multi-Query Attention Pooling for Anomalous Sound Detection

Nan Jiang, Yan Song, Qing Gu, Haoyu Song, Lirong Dai

Towards Few-Shot Training-Free Anomaly Sound Detection

Ho-Hsiang Wu, Wei-Cheng Lin, Abinaya Kumar, Luca Bondi, Shabnam Ghaffarzadegan

Adaptive Across-Subcenter Representation Learning for Imbalanced Anomalous Sound Detection

Dong Wang, Jiqing Han, Guibin Zheng, Tieran Zheng, Yongjun He

Dual Orthogonality Sub-center Loss for Enhanced Anomalous Sound Detection

Dong Wang, Jiqing Han, Tieran Zheng, Guibin Zheng, Yongjun He

Investigating Gender Bias in Text-to-Audio Generation Models

Aarish Shah Mohsin, Mohammad Nadeem, Shahab Saquib Sohail, Tughrul Arsalan, Mandar Gogate

Is it all about race?: A Cross-examination of /s/ in a Multilingual (Nigerian) Context

Oluwasegun Amoniyan

Transcribing Diverse Voices: Using Whisper for ICE corpora

Andreas Weilinghoff

Pre-aspiration in Iceland Is Conditioned by Gender/Sex

Meike Rommel, Míša Hejná, Nicole Dehé