Interspeech 2024

1,065 papers

Novel-view Acoustic Synthesis From 3D Reconstructed Rooms

Byeongjoo Ahn, Karren Yang, Brian Hamilton, Jonathan Sheaffer, Anurag Ranjan

RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation

Liam Kelley, Diego Di Carlo, Aditya Arie Nugraha, Mathieu Fontaine, Yoshiaki Bando

Classification of Room Impulse Responses and its application for channel verification and diarization

Yuri Khokhlov, Tatiana Prisyach, Anton Mitrofanov, Dmitry Dutov, Igor Agafonov

ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency

Yafeng Chen, Siqi Zheng, Hui Wang, Luyao Cheng, Qian Chen

To what extent can ASV systems naturally defend against spoofing attacks?

Jee-weon Jung, Xin Wang, Nicholas Evans, Shinji Watanabe, Hye-jin Shim

Reshape Dimensions Network for Speaker Recognition

Ivan Yakovlev, Rostislav Makarov, Andrei Balykin, Pavel Malov, Anton Okhotnikov

Extraction of interpretable and shared speaker-specific speech attributes through binary auto-encoder

Imen Ben-Amor, Jean-Francois Bonastre, Salima Mdhaffar

Collaborative Contrastive Learning for Hypothesis Domain Adaptation

Jen-Tzung Chien, I-Ping Yeh, Man-Wai Mak

Challenging margin-based speaker embedding extractors by using the variational information bottleneck

Themos Stafylakis, Anna Silnova, Johan Rohdin, Oldřich Plchot, Lukas Burget

Speech emotion recognition with deep learning beamforming on a distant human-robot interaction scenario

Ricardo Garcia, Rodrigo Mahu, Nicolás Grágeda, Alejandro Luzanto, Nicolas Bohmer

Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition

Oliver Schrüfer, Manuel Milling, Felix Burkhardt, Florian Eyben, Björn Schuller

An Investigation of Group versus Individual Fairness in Perceptually Fair Speech Emotion Recognition

Woan-Shiuan Chien, Chi-Chun Lee

Iterative Prototype Refinement for Ambiguous Speech Emotion Recognition

Haoqin Sun, Shiwan Zhao, Xiangyu Kong, Xuechen Wang, Hui Wang

The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability

James Tavernor, Yara El-Tawil, Emily Mower Provost

An Inter-Speaker Fairness-Aware Speech Emotion Regression Framework

Hsing-Hang Chou, Woan-Shiuan Chien, Ya-Tse Wu, Chi-Chun Lee

Dual-Constrained Dynamical Neural ODEs for Ambiguity-aware Continuous Emotion Prediction

Jingyao Wu, Ting Dang, Vidhyasaharan Sethu, Eliathamby Ambikairajah

Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge

Rui Liu, Zening Ma

On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations

Yaqian Hao, Chenguang Hu, Yingying Gao, Shilei Zhang, Junlan Feng

Acoustical analysis of the initial phones in speech-laugh

Ryo Setoguchi, Yoshiko Arimoto

Who Finds This Voice Attractive? A Large-Scale Experiment Using In-the-Wild Data

Hitoshi Suda, Aya Watanabe, Shinnosuke Takamichi

Confidence Estimation for Automatic Detection of Depression and Alzheimer’s Disease Based on Clinical Interviews

Wen Wu, Chao Zhang, Philip C. Woodland

Speaking of Health: Leveraging Large Language Models to assess Exercise Motivation and Behavior of Rehabilitation Patients

Suhas Bn, Amanda Rebar, Saeed Abdullah

Pitch-driven adjustments in tongue positions: Insights from ultrasound imaging

May Pik Yu Chan, Jianjing Kuang

Collecting Mandible Movement in Brazilian Portuguese

Donna Erickson, Albert Rilliard, Malin Svensson Lundmark, Adelaide Silva, Leticia Rebollo Couto

Aerodynamics of Sakata labial-velar oral stops

Lorenzo Maselli, Véronique Delvaux

Revisiting Pitch Jumps: F0 Ratio in Seoul Korean

Michaela Watkins, Paul Boersma, Silke Hamann

Key Acoustic Cues for the Realization of Metrical Prominence in Tone Languages: A Cross-Dialect Study

Yiying Hu, Hui Feng

Frication noise features of Polish voiceless dental fricative and affricate produced by children with and without speech disorder

Zuzanna Miodonska, Michal Kręcichwost, Ewa Kwaśniok, Agata Sage, Pawel Badura

Temporal Co-Registration of Simultaneous Electromagnetic Articulography and Electroencephalography for Precise Articulatory and Neural Data Alignment

Daniel Friedrichs, Monica Lancheros, Sam Kirkham, Lei He, Andrew Clark

Glottal inverse filtering and vocal tract tuning for the numerical simulation of vowel /a/ with different levels of vocal effort

Marc Freixes, Marc Arnela, Joan Claudi Socoró, Luis Joglar-Ongay, Oriol Guasch

On The Performance of EMA-synchronized Speech and Stand-alone Speech in Acoustic-to-articulatory Inversion

Qiang Fang

Measurement and simulation of pressure losses due to airflow in vocal tract models

Peter Birkholz, Patrick Häsner

A comparative study of the impact of voiceless alveolar and palato-alveolar sibilants in English on lip aperture and protrusion during VCV production

Chetan Sharma, Vaishnavi Chandwanshi, Prasanta Kumar Ghosh

Towards a Quantitative Analysis of Coarticulation with a Phoneme-to-Articulatory Model

Chaofei Fan, Jaimie M. Henderson, Chris Manning, Francis R. Willett

On the Encoding of Gender in Transformer-based ASR Representations

Aravind Krishnan, Badr M. Abdullah, Dietrich Klakow

Articulatory Configurations across Genders and Periods in French Radio and TV archives

Benjamin Elie, David Doukhan, Rémi Uro, Lucas Ondel-Yang, Albert Rilliard

Voice Quality Variation in AAE: An Additional Challenge for Addressing Bias in ASR Models?

Li-Fang Lai, Nicole Holliday

Speech After Gender: A Trans-Feminine Perspective on Next Steps for Speech Science and Technology

Robin Netzorg, Alyssa Cote, Sumi Koshin, Klo Vivienne Garoute, Gopala Krishna Anumanchipalli

An inclusive approach to creating a palette of synthetic voices for gender diversity

Eva Szekely, Maxwell Hope

Acoustic Effects of Facial Feminisation Surgery on Speech and Singing: A Case Study

Cliodhna Hughes, Guy Brown, Ning Ma, Nicola Dibben

Gender Representation in TV and Radio: Automatic Information Extraction methods versus Manual Analyses

David Doukhan, Léna Dodson, Manon Conan, Valentin Pelloin, Aurélien Clamouse

Automatic Classification of News Subjects in Broadcast News: Application to a Gender Bias Representation Analysis

Valentin Pelloin, Léna Dodson, Emile Chapuis, Nicolas Hervé, David Doukhan

Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices.

Atli Sigurgeirsson, Eddie L. Ungless

Challenges of German Speech Recognition: A Study on Multi-ethnolectal Speech Among Adolescents

Martha Schubert, Daniel Duran, Ingo Siegert

Voice Disorder Analysis: a Transformer-based Approach

Alkis Koudounas, Gabriele Ciravegna, Marco Fantini, Erika Crosetti, Giovanni Succo

Prosody-Driven Privacy-Preserving Dementia Detection

Dominika Woszczyk, Ranya Aloufi, Soteris Demetriou

Analyzing Multimodal Features of Spontaneous Voice Assistant Commands for Mild Cognitive Impairment Detection

Nana Lin, Youxiang Zhu, Xiaohui Liang, John A. Batsis, Caroline Summerour

Detection of Cognitive Impairment And Alzheimer's Disease Using a Speech- and Language-Based Protocol

Tanya Talkar, Sherman Charles, Chelsea Krantsevich, Kan Kawabata

Investigation of Layer-Wise Speech Representations in Self-Supervised Learning Models: A Cross-Lingual Study in Detecting Depression

Bubai Maji, Rajlakshmi Guha, Aurobinda Routray, Shazia Nasreen, Debabrata Majumdar

Quantifying the effect of speech pathology on automatic and human speaker verification

Bence Mark Halpern, Thomas Tienkamp, Wen-Chin Huang, Lester Phillip Violeta, Teja Rebernik

Sparse Binarization for Fast Keyword Spotting

Jonathan Svirsky, Uri Shaham, Ofir Lindenbaum

VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech

Ashishkumar Gudmalwar, Nirmesh Shah, Sai Akarsh, Pankaj Wasnik, Rajiv Ratn Shah

Acceleration of Posteriorgram-based DTW by Distilling the Class-to-class Distances Encoded in the Classifier Used to Calculate Posteriors

Haitong Sun, Jaehyun Choi, Nobuaki Minematsu, Daisuke Saito

Prompting Large Language Models with Mispronunciation Detection and Diagnosis Abilities

Minglin Wu, Jing Xu, Xixin Wu, Helen Meng

Text Injection for Neural Contextual Biasing

Zhong Meng, Zelin Wu, Rohit Prabhavalkar, Cal Peyser, Weiran Wang

Towards interfacing large language models with ASR systems using confidence measures and prompting

Maryam Naderi, Enno Hermann, Alexandre Nanchen, Sevada Hovsepyan, Mathew Magimai.-Doss

Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps

Mattias Nilsson, Riccardo Miccini, Clement Laroche, Tobias Piechowiak, Friedemann Zenke

GSQA: An End-to-End Model for Generative Spoken Question Answering

Min-Han Shih, Ho-Lam Chung, Yu-Chi Pai, Ming-Hao Hsu, Guan-Ting Lin

Contextual Interactive Evaluation of TTS Models in Dialogue Systems

Siyang Wang, Eva Szekely, Joakim Gustafson

DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing

Neha Sahipjohn, Ashishkumar Gudmalwar, Nirmesh Shah, Pankaj Wasnik, Rajiv Ratn Shah

Joint Learning of Context and Feedback Embeddings in Spoken Dialogue

Livia Qian, Gabriel Skantze

ConvoCache: Smart Re-Use of Chatbot Responses

Conor Atkins, Ian Wood, Mohamed Ali Kaafar, Hassan Asghar, Nardine Basta

Autoregressive cross-interlocutor attention scores meaningfully capture conversational dynamics

Matthew McNeill, Rivka Levitan

Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert

Han EunGi, Oh Hyun-Bin, Kim Sung-Bin, Corentin Nivelet Etcheberry, Suekyeong Nam

Zero-Shot Fake Video Detection by Audio-Visual Consistency

Xiaolou Li, Zehua Liu, Chen Chen, Lantian Li, Li Guo

LLM-Driven Multimodal Opinion Expression Identification

Bonian Jia, Huiyao Chen, Yueheng Sun, Meishan Zhang, Min Zhang

SAMSEMO: New dataset for multilingual and multimodal emotion recognition

Pawel Bujnowski, Bartlomiej Kuzma, Bartlomiej Paziewski, Jacek Rutkowski, Joanna Marhula

Spoken Word2Vec: Learning Skipgram Embeddings from Speech

Mohammad Amaan Sayeed, Hanan Aldarmaki

Spontaneous Speech-Based Suicide Risk Detection Using Whisper and Large Language Models

Ziyun Cui, Chang Lei, Wen Wu, Yinan Duan, Diyang Qu

SWAN: SubWord Alignment Network for HMM-free word timing estimation in end-to-end automatic speech recognition

Woo Hyun Kang, Srikanth Vishnubhotla, Rudolf Braun, Yogesh Virkar, Raghuveer Peri

Quantifying Unintended Memorization in BEST-RQ ASR Encoders

Virat Shejwalkar, Om Thakkar, Arun Narayanan

Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting

Yosuke Kashiwagi, Hayato Futami, Emiru Tsunoo, Siddhant Arora, Shinji Watanabe

Efficient and Robust Long-Form Speech Recognition with Hybrid H3-Conformer

Tomoki Honda, Shinsuke Sakai, Tatsuya Kawahara

Online Knowledge Distillation of Decoder-Only Large Language Models for Efficient Speech Recognition

Jeehye Lee, Hyeji Seo

ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2vec2.0 Based ASR

Vishwanath Pratap Singh, Federico Malato, Ville Hautamäki, Md. Sahidullah, Tomi Kinnunen

Online Subloop Search via Uncertainty Quantization for Efficient Test-Time Adaptation

Jae-Hong Lee, Sang-Eon Lee, Dong-Hyun Kim, Dohee Kim, Joon-Hyuk Chang

Speaker Personalization for Automatic Speech Recognition using Weight-Decomposed Low-Rank Adaptation

George Joseph, Arun Baby

Personality-memory Gated Adaptation: An Efficient Speaker Adaptation for Personalized End-to-end Automatic Speech Recognition

Yue Gu, Zhihao Du, Shiliang Zhang, Jiqing Han, Yongjun He

Self-training ASR Guided by Unsupervised ASR Teacher

Hyung Yong Kim, Byeong-Yeol Kim, Yunkyu Lim, Jihwan Park, Shukjae Choi

Boosting CTC-based ASR using inter-layer attention-based CTC loss

Keigo Hojo, Yukoh Wakabayashi, Kengo Ohta, Atsunori Ogawa, Norihide Kitaoka

Hierarchical Multi-Task Learning with CTC and Recursive Operation

Nahomi Kusunoki, Yosuke Higuchi, Tetsuji Ogawa, Tetsunori Kobayashi

Dual-path Adaptation of Pretrained Feature Extraction Module for Robust Automatic Speech Recognition

Hao Shi, Tatsuya Kawahara

Unsupervised Online Continual Learning for Automatic Speech Recognition

Steven Vander Eeckt, Hugo Van hamme

Self-Train Before You Transcribe

Robert Flynn, Anton Ragni

LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks

Amit Meghanani, Thomas Hain

Convolution-Augmented Parameter-Efficient Fine-Tuning for Speech Recognition

Kwangyoun Kim, Suwon Shon, Yi-Te Hsu, Prashant Sridhar, Karen Livescu

Speech and Language Recognition with Low-rank Adaptation of Pretrained Models

Amrutha Prasad, Srikanth Madikeri, Driss Khalil, Petr Motlicek, Christof Schuepbach

MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization

Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma, Lu Yin, Qiao Xiao

Beyond graphemes and phonemes: continuous phonological features in neural text-to-speech synthesis

Christina Tånnander, Shivam Mehta, Jonas Beskow, Jens Edlund

Positional Description for Numerical Normalization

Deepanshu Gupta, Javier Latorre

Learning Pronunciation from Other Accents via Pronunciation Knowledge Transfer

Siqi Sun, Korin Richmond

G2PA: G2P with Aligned Audio for Mandarin Chinese

Xingxing Yang

Audio-conditioned phonemic and prosodic annotation for building text-to-speech models from unlabeled speech data

Yuma Shirahata, Byeongseon Park, Ryuichi Yamamoto, Kentaro Tachibana

Enhancing Japanese Text-to-Speech Accuracy with a Novel Combination Transformer-BERT-based G2P: Integrating Pronunciation Dictionaries and Accent Sandhi

Kiyoshi Kurihara, Masanori Sano

Homograph Disambiguation with Text-to-Text Transfer Transformer

Markéta Řezáčková, Daniel Tihelka, Jindřich Matoušek

Exploring the Benefits of Tokenization of Discrete Acoustic Units

Avihu Dekel, Raul Fernandez

A Language Modeling Approach to Diacritic-Free Hebrew TTS

Amit Roth, Arnon Turetzky, Yossi Adi

LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance

Shihao Chen, Yu Gu, Jie Zhang, Na Li, Rilin Chen

Disentangling prosody and timbre embeddings via voice conversion

Nicolas Gengembre, Olivier Le Blouch, Cedric Gendrot

Residual Speaker Representation for One-Shot Voice Conversion

Le Xu, Jiangyan Yi, Tao Wang, Yong Ren, Rongxiu Zhong