Interspeech 2025

1,156 papers

Top Research Directions

Research directions most represented by Interspeech 2025 papers.

Partitioning Variance with Linear Mixed Effects Models 44
Learning High-Level Acoustic Structures from Unlabeled Audio 42
Mitigating the Acoustic Mismatch in Atypical Speech Recognition 35
Fine Tuning Speech Models for Specialized Domains 28
Factorizing Speech into Content Timbre and Prosody 25
Overcoming Data Scarcity in Low-Resource Speech Recognition 25
Overcoming the Modality Gap in Audio Language Models 19
Synergistic Multi Task Learning for Speech and Audio 18
The Perceptual Evaluation Gap in Generative Audio 18
Temporal Alignment of Speech and Text 17
Fine-Grained Prosodic Control for Expressive Speech Synthesis 17
Generalizing from Limited Cohorts in Speech Research 17
Speech Analysis for Early Detection of Cognitive Decline 16
Zero Shot Speaker Generalization for Speech Synthesis 16
Mitigating Data Scarcity in Affective Speech Models 16

Top Authors

AuthorPapers
Shinji Watanabe22
Haizhou Li10
Shrikanth Narayanan10
Yanmin Qian10
Dong Yu9
Hung-yi Lee8
EngSiong Chng7
Sabato Marco Siniscalchi6
Xiaofen Xing6
Xixin Wu6
Bin Ma5
Jagadeesh Balam5
Jian Luan5
Joon-Hyuk Chang5
Kyogu Lee5
Man-Wai Mak5
Najim Dehak5
Shujie HU5
Yifan Peng5
Chenxing Li4

Impactful Papers

Papers from Interspeech 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
Tracking /r/ Deletion: Forced Alignment of Pronunciation Variants and Sociophonetic Insights into Post-Obstruent Final /r/ in French
Training Articulatory Inversion Models for Interspeaker Consistency
Training-Free Voice Conversion with Factorized Optimal Transport
Training Onset-and-Offset-Aware Sound Event Detection on a Heterogeneous Dataset via Probabilistic Sequential Modeling
Transcribing Diverse Voices: Using Whisper for ICE corpora
Transcribing Oral History Recordings Using the Transcription Portal
Transcript-Prompted Whisper with Dictionary-Enhanced Decoding for Japanese Speech Annotation
Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems
TS3-Codec: Transformer-Based Simple Streaming Single Codec
TSDT-Net: Ultra-Low-Complexity Two-Stage Model Combining Dual-Path-Transformer and Transform-Average-Concatenate Network for Speech Enhancement
TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network
TTMBA: Towards Text To Multiple Sources Binaural Audio Generation
Tungnaá In Live Performance: An Implementation Of Interactive Artistic Text-To-Voice
Turing's Echo: Investigating Linguistic Sensitivity of Deepfake Voice Detection via Gamification
TVC-MusicGen: Time-Varying Structure Control for Background Music Generation via Self-Supervised Training
Ultra-Low Bit Post-Training Quantization of Large Speech Models via K-Means Clustering and Mixed Precision Allocation
Understanding Dementia Speech Alignment with Diffusion-Based Image Generation
Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models
Unified Audio-Visual Modeling for Recognizing Which Face Spoke When and What in Multi-Talker Overlapped Speech and Video
Unified Microphone Conversion: Many-to-Many Device Mapping via Feature-wise Linear Modulation
Unified Semi-Supervised Pipeline for Automatic Speech Recognition
Unified Text and Speaker Verification using SSL model for Text-Dependent Speaker Verification
Unified Variational and Physics-aware Model for Room Impulse Response Estimation
Unifying Listener Scoring Scales: Comparison Learning Framework for Speech Quality Assessment and Continuous Speech Emotion Recognition
Universal Preference-Score-based Pairwise Speech Quality Assessment
Universal Speech Enhancement with Regression and Generative Mamba
Uni-VERSA: Versatile Speech Assessment with a Unified Network
Unlearning LLM-Based Speech Recognition Models
Unleashing the Inner Monster: Demonstrating High-Fidelity Human to Non-Human Voice Conversion
Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
Unmasking real-world audio deepfakes: A data-centric approach
Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech
Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusion
U-SAM: An Audio Language Model for Unified Speech, Audio, and Music Understanding
Using and comprehending language in face-to-face conversation
Using gender, phonation and age to interpret automatically discovered speech attributes for explainable speaker recognition
Using Neurogram Similarity Index Measure (NSIM) to Model Hearing Loss and Cochlear Neural Degeneration
Variability in Intervocalic /t/ and Community Diversity in Australian English
Variability in performance across four generations of automatic speaker recognition systems
VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset
Vector Quantized Cross-lingual Unsupervised Domain Adaptation for Speech Emotion Recognition
Vela: Scalable Embeddings with Voice Large Language Models for Multimodal Retrieval
VIB-based Real Pre-emphasis Audio Deepfake Source Tracing
VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion
ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition
Video-to-Audio Generation with Fine-grained Temporal Semantics
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
Vision-Integrated High-Quality Neural Speech Coding
Visual Cues Support Robust Turn-taking Prediction in Noise
Visual features of the oral region in Polish sibilants produced by children with various sibilance patterns

« prev Page 22/24 next »