Interspeech 2024

1,036 papers

Top Research Directions

Research directions most represented by Interspeech 2024 papers.

Learning High-Level Acoustic Structures from Unlabeled Audio 50
Partitioning Variance with Linear Mixed Effects Models 27
Fine Tuning Speech Models for Specialized Domains 22
Overcoming the Modality Gap in Audio Language Models 19
Mitigating the Acoustic Mismatch in Atypical Speech Recognition 19
Overcoming Data Scarcity in Low-Resource Speech Recognition 19
Zero Shot Speaker Generalization for Speech Synthesis 18
Resolving Overlapping Speech in Multi-Speaker Audio 18
The Single Speaker Generalization Bottleneck in Speech Synthesis 18
Temporal Alignment of Speech and Text 17
Speech Analysis for Early Detection of Cognitive Decline 17
Layer Specialization in Deep Speech Representations 16
Visual Anchoring for Robust Speech Enhancement 15
Low-Rank Weight Decomposition for Efficient Model Adaptation 15
Parameter Efficient Speech and Audio Processing 14

Top Authors

AuthorPapers
Shinji Watanabe24
Joon-Hyuk Chang11
Haizhou Li10
Jiatong Shi10
Helen M. Meng9
Jianhua Tao9
Lei Xie9
Hung-yi Lee8
Xixin Wu7
Yanmin Qian7
Chao Zhang6
Xie Chen6
Zhengqi Wen6
EngSiong Chng5
Junlan Feng5
Shrikanth Narayanan5
Yossi Adi5
Yuxun Tang5
Zengrui Jin5
Zhen-Hua Ling5

Impactful Papers

Papers from Interspeech 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
On the social bias of speech self-supervised models
On the Success and Limitations of Auxiliary Network Based Word-Level End-to-End Neural Speaker Diarization
On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models
On the Use of Plausible Arguments in Explainable Conversational AI
Optical Flow Guided Tongue Trajectory Generation for Diffusion-based Acoustic to Articulatory Inversion
Optimizing Automatic Speech Assessment: W-RankSim Regularization and Hybrid Feature Fusion Strategies
Optimizing Large-Scale Context Retrieval for End-to-End ASR
Optimizing the role of human evaluation in LLM-based spoken document summarization systems
OR-TSE: An Overlap-Robust Speaker Encoder for Target Speech Extraction
Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models
Out-of-distribution generalisation in spoken language understanding
Oversampling, Augmentation and Curriculum Learning for Speaking Assessment with Limited Training Data
OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
PAM: Prompting Audio-Language Models for Audio Quality Assessment
ParaCLAP – Towards a general language-audio model for computational paralinguistic tasks
Parameter-Efficient Adapter Based on Pre-trained Models for Speech Translation
Parameter-efficient Fine-tuning of Speaker-Aware Dynamic Prompts for Speaker Verification
PARAN: Variational Autoencoder-based End-to-End Articulation-to-Speech System for Speech Intelligibility
PARIS: Pseudo-AutoRegressIve Siamese Training for Online Speech Separation
Participant-Pair-Wise Bottleneck Transformer for Engagement Estimation from Video Conversation
Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition
Perception of music and speech: Focus on rhythm processing
Perceptual Learning in Lexical Tone: Phonetic Similarity vs. Phonological Categories
Performant ASR Models for Medical Entities in Accented Speech
Period Singer: Integrating Periodic and Aperiodic Variational Autoencoders for Natural-Sounding End-to-End Singing Voice Synthesis
PERSONA: an application for emotion recognition, gender recognition and age estimation
Personality-memory Gated Adaptation: An Efficient Speaker Adaptation for Personalized End-to-end Automatic Speech Recognition
Personalized Speech Enhancement Without a Separate Speaker Embedding Model
PFCA-Net: Pyramid Feature Fusion and Cross Content Attention Network for Automated Audio Captioning
Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
PhoneViz: exploring alignments at a glance
Phonological Feature Detection for US English using the Phonet Library
Phonological-Level Mispronunciation Detection and Diagnosis
Phonological Symmetry Does Not Predict Generalization of Perceptual Adaptation to Vowels
Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models
Pitch-Aware RNN-T for Mandarin Chinese Mispronunciation Detection and Diagnosis
Pitch-driven adjustments in tongue positions: Insights from ultrasound imaging
PitchFlow: adding pitch control to a Flow-matching based TTS model
PLDNet: PLD-Guided Lightweight Deep Network Boosted by Efficient Attention for Handheld Dual-Microphone Speech Enhancement
PL-TTS: A Generalizable Prompt-based Diffusion TTS Augmented by Large Language Model
Positional Description for Numerical Normalization
Post-Net: A linguistically inspired sequence-dependent transformed neural architecture for automatic syllable stress detection
PPPR: Portable Plug-in Prompt Refiner for Text to Audio Generation
Pragmatically similar utterance finder demonstration
Predefined Prototypes for Intra-Class Separation and Disentanglement
Predicting Acute Pain Levels Implicitly from Vocal Features
Predicting Heart Activity from Speech using Data-driven and Knowledge-based features
Preliminary Investigation of Psychometric Properties of a Novel Multimodal Dialog Based Affect Production Task in Children and Adolescents with Autism
Preprocessing for acoustic-to-articulatory inversion using real-time MRI movies of Japanese speech

« prev Page 14/21 next »