Interspeech 2025

1,179 papers

Identification of Pathological Pronunciation Profiles in ASR Transcription Errors

Margot Masson, Isabelle Ferrané, Julie Mauclair

Fine-tuning Strategies for Automatic Speech Recognition of Low-Resource Speech with Autism Spectrum Disorder

Yeseul Park, Bowon Lee

Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency Detection

Jinming Zhang, Xuanru Zhou, Jiachen Lian, Shuhe Li, William Li

Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis

Zongli Ye, Jiachen Lian, Xuanru Zhou, Jinming Zhang, Haodong Li

Leveraging LLM for Stuttering Speech: A Unified Architecture Bridging Recognition and Event Detection

Shangkun Huang, Jing Deng, Jintao Kang, Rong Zheng

Unified Audio-Visual Modeling for Recognizing Which Face Spoke When and What in Multi-Talker Overlapped Speech and Video

Naoki Makishima, Naotaka Kawata, Taiga Yamane, Mana Ihori, Tomohiro Tanaka

Efficient Noise-Robust Hybrid Audiovisual Encoder with Joint Distillation and Pruning for Audiovisual Speech Recognition

Zhengyang Li, Pascal Reichert, Thomas Graave, Patrick Blumenberg, Tim Fingscheidt

Cocktail-Party Audio-Visual Speech Recognition

Thai-Binh Nguyen, Ngoc-Quan Pham, Alexander Waibel

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach

Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna, Alessio Brutti

Text Entry for All: Towards Speech-based Multimodal Interaction for Inclusion, Accessibility and the Preservation of the World’s Linguistic Heritage

Julian Zapata, Lara Hanna

How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not

Francesco Verdini, Pierfrancesco Melucci, Stefano Perna, Francesco Cariaggi, Marco Gaido

Is Synthetic Data Truly Effective for Training Speech Language Models?

Tomoya Mizumoto, Atsushi Kojima, Yusuke Fujita, Lianbo Liu, Yui Sudo

Evaluating ASR Robustness to Spontaneous Speech Errors: A Study of WhisperX Using a Speech Error Database

John Alderete, Macarious Kin Fung Hui, Aanchan Mohan

Uni-VERSA: Versatile Speech Assessment with a Unified Network

Jiatong Shi, Hye-jin Shim, Shinji Watanabe

Continual Speech Learning with Fused Speech Features

Guitao Wang, Jinming Zhao, Hao Yang, Guilin Qi, Tongtong Wu

SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information

Chih-Kai Yang, Neo Ho, Yen-Ting Piao, Hung-yi Lee

Towards a Japanese Full-duplex Spoken Dialogue System

Atsumoto Ohashi, Shinya Iizuka, Jingjing Jiang, Ryuichiro Higashinaka

I want a horror – comedy – movie: Slips-of-the-Tongue Impact Conversational Recommender System Performance

Maria Teleki, Lingfeng Shi, Chengkai Liu, James Caverlee

Evaluating Large Language Models in Data Generation for Low-Resource Scenarios: A Case Study on Question Answering

Ebru Arisoy, Merve Ünlü Menevşe, Yusufcan Manav, Arzucan Özgür

``Alexa, can you forget me?'' Machine Unlearning Benchmark in Spoken Language Understanding

Alkis Koudounas, Claudio Savelli, Flavio Giobergia, Elena Baralis

Who, When, and What: Leveraging the ``Three Ws'' Concept for Emotion Recognition in Conversation

Xiaohan Shi, Xingfeng Li, Tomoki Toda

SpeechDialogueFactory: A Framework for Natural Speech Dialogue Generation

Minghan Wang, Ye Bai, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi

What Do Humans Hear When Interacting? Experiments on Selective Listening for Evaluating ASR of Spoken Dialogue Systems

Kiyotada Mori, Seiya Kawano, Chaoran Liu, Carlos Toshinori Ishi, Angel Garcia Contreras

Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs

Šimon Sedláček, Bolaji Yusuf, Jan Švec, Pradyoth Hegde, Santosh Kesiraju

Leveraging LLMs for Written to Spoken Style Data Transformation to Enhance Spoken Dialog State Tracking

Haris Gulzar, Monikka Roslianna Busto, Akiko Masaki, Takeharu Eda, Ryo Masumura

PruneSLU: Efficient On-device Spoken Language Understanding through Vocabulary and Structural Pruning

Truong Do, Minh-Phuong Nguyen, Le -Minh Nguyen

From Speech Science to Language Transparence

Alexander Waibel

SLASH: Self-Supervised Speech Pitch Estimation Leveraging DSP-derived Absolute Pitch

Ryo Terashima, Yuma Shirahata, Masaya Kawamura

Robust Vocal Intensity Prediction: Overcoming Dataset Bias with Pretrained Deep Models

Quentin Le Tellier, Marc Evrard, Albert Rilliard, Jean-Sylvain Liénard

Significance of Time-Frequency preprocessing for automatic Ultrasonic Vocalization classification in Autism Spectrum Disorder model detection

Szymon Szmajdziński, Juliusz Wójtowicz-Kruk, Ivan Ryzhankow, Łukasz Łazarski, Jakub Żak

MADUV: The 1st INTERSPEECH Mice Autism Detection via Ultrasound Vocalization Challenge

Zijiang Yang, Meishu Song, Xin Jing, Haojie Zhang, Kun Qian

Exploring Pre-trained models on Ultrasound Modeling for Mice Autism Detection with Uniform Filter Bank and Attentive Scoring

Yuchen Song, Yucong Zhang, Ming Li

Exploring the Power of Empirical Mode Decomposition for Sensing the Sound of Silence: A Pilot Study on Mice Autism Detection via Ultrasonic Vocalisation

Chenhao Wu, Xiangjun Cai, Haojie Zhang, Tianrui Jia, Yilu Deng

Improving Bird Classification with Primary Color Additives

Ezhini Rasendiran R, Chandresh Kumar Maurya

Dog2vec: Self-Supervised Pre-Training for Canine Vocal Representation

Xingyuan Li, Kenny Zhu, Mengyue Wu

Analysis of Avian Biphonic Vocalization Using Computational Modelling

Noumida A, Rajeev Rajan

DLF-EEND: Dynamic Layer Fusion for End-to-End Speaker Diarization

Wooil Kim, Bongsu Jung

Joint Target-Speaker ASR and Activity Detection

Chikara Maeda, Muhammad Shakeel, Yui Sudo

Multimodal Zero-Shot Framework for Deepfake Hate Speech Detection in Low-Resource Languages

Rishabh Ranjan, Likhith Ayinala, Mayank Vatsa, Richa Singh

Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models

Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar, Swarup Ranjan Behera, Priyabrata Mallick

A Siamese Network-Based Framework for Voice Mimicry Proficiency Assessment Using X-Vector Embeddings

Bhasi K.C., Rajeev Rajan

Mimic Blocker: Self-Supervised Adversarial Training for Voice Conversion Defense with Pretrained Feature Extractors

Gwangyeol Yu, Junhyeok Lee, Seoryeong Kim, Jimin Lee, Jehyuk Lee

Towards Secure User Authentication for Headphones via In-Ear or In-Earcup Microphones

N Shashaank, Xiao Quan, Andrew Kaluzny, Leonard Varghese, Marko Stamenovic

Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM

Zhaokai Sun, Li Zhang, Qing Wang, Pan Zhou, Lei Xie

Unified Text and Speaker Verification using SSL model for Text-Dependent Speaker Verification

Nathan Griot, Driss Matrouf, Raphael Blouet, Jean-Francois Bonastre, Ana Mantecon

Parameter-Efficient Fine-tuning with Instance-Aware Prompt and Parallel Adapters for Speaker Verification

Shengyu Peng, Wu Guo, Jie Zhang, Yu Guan, Lipeng Dai

Intrasentential English in Swedish TTS: perceived English-accentedness

Christina Tånnander, David House, Jonas Beskow, Jens Edlund

Synthesizing Speech with Selected Perceptual Voice Qualities – A Case Study with Creaky Voice

Frederik Rautenberg, Fritz Seebauer, Jana Wiechmann, Michael Kuhlmann, Petra Wagner

Developing High-Quality TTS for Punjabi and Urdu: Benchmarking against MMS Models

Fatima Naseem, Maham Sajid, Farah Adeeba, Sahar Rauf, Asad Mustafa

LIST: Language-Independent Speech Token for Multilingual Speech Synthesis with Language Models

Chang Liu, Zhen-Hua Ling, Yu Gu

Accent Normalization Using Self-Supervised Discrete Tokens with Non-Parallel Data

Qibing Bai, Sho Inoue, Shuai Wang, Zhongjie Jiang, Yannan Wang

Parameter-Efficient Fine-Tuning for Low-Resource Text-to-Speech via Cross-Lingual Continual Learning

Ki-Joong Kwon, Jun-Ho So, Sang-Hoon Lee

Pretraining Multi-Speaker Identification for Neural Speaker Diarization

Shota Horiguchi, Atsushi Ando, Naohiro Tawara, Marc Delcroix

Enhancing Serialized Output Training for Multi-Talker ASR with Soft Monotonic Alignment and Utterance-level Timestamp

Fengyun Tan, Tao Wei, Kun Zou, Ning Cheng, Shaojun Wang

SDBench: A Comprehensive Benchmark Suite for Speaker Diarization

Berkin Durmus, Blaise Munyampirwa, Eduardo Pacheco, Atila Orhon, Andrey Leonov

End-to-End Diarization utilizing Attractor Deep Clustering

David Palzer, Matthew Maciejewski, Eric Fosler-Lussier

Count Your Speakers! Multitask Learning for Multimodal Speaker Diarization

Prabhav Singh, Jesus Villalba, Najim Dehak

Fine-tune Before Structured Pruning: Towards Compact and Accurate Self-Supervised Models for Speaker Diarization

Jiangyu Han, Federico Landini, Johan Rohdin, Anna Silnova, Mireia Diez

Open-Set Source Tracing of Audio Deepfake Systems

Nicholas Klein, Hemlata Tak, Elie Khoury

Defending Unauthorized Voice Cloning with Watermark-Aware Codecs

Jiankun Zhao, Lingwei Meng, Chengxi Deng, Helen Meng, Xixin Wu

VIB-based Real Pre-emphasis Audio Deepfake Source Tracing

Thien-Phuc Doan, Kihun Hong, Souhwan Jung

Listen, Analyze, and Adapt to Learn New Attacks: An Exemplar-Free Class Incremental Learning Method for Audio Deepfake Source Tracing

Yang Xiao, Rohan Kumar Das

Synthetic Speech Source Tracing using Metric Learning

Dimitrios Koutsianos, Stavros Zacharopoulos, Yannis Panagakis, Themos Stafylakis

STOPA: A Dataset of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution

Anton Firc, Manasi Chhibber, Jagabandhu Mishra, Vishwanath Pratap Singh, Tomi Kinnunen

Source Verification for Speech Deepfakes

Viola Negroni, Davide Salvi, Paolo Bestagini, Stefano Tubaro

TADA: Training-free Attribution and Out-of-Domain Detection of Audio Deepfakes

Adriana Stan, David Combei, Dan Oneata, Horia Cucu

Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy

Xuanjun Chen, I-Ming Lin, Lin Zhang, JIAWEI DU, Haibin Wu

Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion

Ajinkya Kulkarni, Sandipana Dowerah, Tanel Alumäe, Mathew Magimai Doss

Audio Deepfake Source Tracing using Multi-Attribute Open-Set Identification and Verification

Pierre Falez, Tony Marteau, Damien Lolive, Arnaud Delhay

Federated Learning with Feature Space Separation for Speaker Recognition

Ying Meng, Zhihua Fang, Liang He

Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy

Elvir Karimov, Alexander Varlamov, Danil Ivanov, Dmitrii Korzh, Oleg Rogov

Privacy-Preserving Speaker Verification via End-to-End Secure Representation Learning

Chenguang Hu, Yaqian Hao, Fulin Zhang, Xiaoxue Luo, Yao Shen

An Investigative Study on Recent Sharpness- and Flatness-Based Optimizers for Enhanced Self-Supervised Speaker Verification

Abderrahim Fathan, Jahangir Alam, Xiaolin Zhu

A Study of Speech Embedding Similarities Between Australian Aboriginal and High-Resource Languages

Eliathamby Ambikairajah, Jingyao Wu, Ting Dang, Vidhyasaharan Sethu

Analyzing the Impact of Accent on English Speech: Acoustic and Articulatory Perspectives

Gowtham Premananth, Vinith Kugathasan, Carol Espy-Wilson

LID Models are Actually Accent Classifiers: Implications and Solutions for LID on Accented Speech

Niyati Bafna, Matthew Wiesner

Teacher-Free Knowledge Distillation for Improving Short-Utterance Spoken Language Identification

Spandan Dey, Hirak Mondal, Sanjay Kumar Kurmi

Exploring Efficient Directional and Distance Cues for Regional Speech Separation

Yiheng Jiang, Haoxu Wang, Yafeng Chen, Gang Qiao, Biao Tian

Power Spectral Density Estimation for Acoustic Source Separation Using A Spherical Microphone Array

Liang Tao, Maoshen Jia, Yonggang Hu

FLASepformer: Efficient Speech Separation with Gated Focused Linear Attention Transformer

Haoxu Wang, Yiheng Jiang, Gang Qiao, Pengteng Shi, Biao Tian

Deep-Simplex Multichannel Speech Separation

Tzlil Avidan, Bracha Laufer-Goldshtein

ReSepNet: A Unified-Light Model for Recursive Speech Separation with Unknown Speaker Count

Hadi Alizadeh, Rahil Mahdian Toroghi, Hassan Zareian

Attractor-Based Speech Separation of Multiple Utterances by Unknown Number of Speakers

Yuzhu Wang, Archontis Politis, Konstantinos Drossos, Tuomas Virtanen

Speaker Separation for an Unknown Number of Speakers with Encoder-Decoder-Based Contextual Information Module

Xue Yang, Guiru Shen, Yu Yang

End-to-End DOA-Guided Speech Extraction in Noisy Multi-Talker Scenarios

Kangqi Jing, Wenbin Zhang, Yu Gao

Quadruple Path Modeling with Latent Feature Transfer for Permutation-free Continuous Speech Separation

Jihyun Kim, Doyeon Kim, Hyewon Han, Jinyoung Lee, Jonguk Yoo

ClaritySpeech: Dementia Obfuscation in Speech

Dominika C Woszczyk, Ranya Aloufi, Soteris Demetriou

Understanding Dementia Speech Alignment with Diffusion-Based Image Generation

Mansi, Anastasios Lepipas, Dominika C Woszczyk, Yiying Guan, Soteris Demetriou

Alzheimer’s Dementia Detection Using Perplexity from Paired Large Language Models

Yao Xiao, Heidi Christensen, Stefan Goetze

Acoustic and Linguistic Biomarkers for Cognitive Impairment Detection from Speech

Catarina Botelho, David Gimeno-Gómez, Francisco Teixeira, John Mendonça, Patrícia Pereira

WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper

Emmanuel Akinrintoyo, Nadine Abdelhalim, Nicole Salomons

Optimizing Pause Context in Fine-Tuning Pre-trained Large Language Models for Dementia Detection

Xiaoquan KE, Man-Wai Mak, Helen Meng

Speaker Normalization and Content Restoration for Zero-Shot Voice Conversion with Attention-Enhanced Discriminator

Desheng Hu, Yang Xiang, Jian Lu, Xinhui Hu, Xinkang Xu

LinearVC: Linear Transformations of Self-Supervised Features Through the Lens of Voice Conversion

Herman Kamper, Benjamin Van Niekerk, Julian Zaïdi, Marc-André Carbonneau

In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion

Jiawei Jin, Zhihan Yang, Yixuan Zhou, Zhiyong Wu

ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization

Pengyu Ren, Wenhao Guan, Kaidi Wang, Peijie Chen, Qingyang Hong

Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion

Kaidi Wang, Wenhao Guan, Ziyue Jiang, Hukai Huang, Peijie Chen

E2E-BPVC: End-to-End Background-Preserving Voice Conversion via In-Context Learning

Yihan Liu, Zhengyang Chen, Leying Zhang, Yanmin Qian

Training-Free Voice Conversion with Factorized Optimal Transport

Alexander Lobashev, Assel Yermekova, Maria Larchenko

REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion

Ishan D. Biyani, Nirmesh J. Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik, Rajiv R. Shah