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
Reshape Dimensions Network for Speaker Recognition
Residual Speaker Representation for One-Shot Voice Conversion
Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps
Retrieval-Augmented Classifier Guidance for Audio Generation
Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining
Revealing Confounding Biases: A Novel Benchmarking Approach for Aggregate-Level Performance Metrics in Health Assessments
Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis
Revisiting Convolution-free Transformer for Speech Recognition
Revisiting Pitch Jumps: F0 Ratio in Seoul Korean
RevRIR: Joint Reverberant Speech and Room Impulse Response Embedding using Contrastive Learning with Application to Room Shape Classification
Rich speech signal: exploring and exploiting end-to-end automatic speech recognizers' ability to model hesitation phenomena
RIR-in-a-Box: Estimating Room Acoustics from 3D Mesh Data through Shoebox Approximation
RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios
ROAR: Reinforcing Original to Augmented Data Ratio Dynamics for Wav2vec2.0 Based ASR
Robust Laughter Segmentation with Automatic Diverse Data Synthesis
Robust spread spectrum speech watermarking using linear prediction and deep spectral shaping
RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement
SALSA: Speedy ASR-LLM Synchronous Aggregation
SAML: Speaker Adaptive Mixture of LoRA Experts for End-to-End ASR
Sample-Efficient Diffusion for Text-To-Speech Synthesis
SAMSEMO: New dataset for multilingual and multimodal emotion recognition
SaSLaW: Dialogue Speech Corpus with Audio-visual Egocentric Information Toward Environment-adaptive Dialogue Speech Synthesis
SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech
Scaling up masked audio encoder learning for general audio classification
SCDNet: Self-supervised Learning Feature based Speaker Change Detection
Schrödinger Bridge for Generative Speech Enhancement
Schrödinger Bridge for Generative Speech Enhancement
SC-MoE: Switch Conformer Mixture of Experts for Unified Streaming and Non-streaming Code-Switching ASR
SDAEC: Signal Decoupling for Advancing Acoustic Echo Cancellation
Seamless Language Expansion: Enhancing Multilingual Mastery in Self-Supervised Models
Searching for Structure: Appraising the Organisation of Speech Features in wav2vec 2.0 Embeddings
SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures
Segmental and Suprasegmental Speech Foundation Models for Classifying Cognitive Risk Factors: Evaluating Out-of-the-Box Performance
Self-Supervised Embeddings for Detecting Individual Symptoms of Depression
Self-Supervised Learning for ASR Pre-Training with Uniquely Determined Target Labels and Controlling Cepstrum Truncation for Speech Augmentation
Self-Supervised Learning with Multi-Head Multi-Mode Knowledge Distillation for Speaker Verification
Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning
Self-Supervised Speaker Verification with Mini-Batch Prediction Correction
Self-supervised speaker verification with relational mask prediction
Self-Supervised Speech Representations are More Phonetic than Semantic
Self-supervised Speech Representations Still Struggle with African American Vernacular English
Self-Train Before You Transcribe
Self-training ASR Guided by Unsupervised ASR Teacher
SELM: Enhancing Speech Emotion Recognition for Out-of-Domain Scenarios
SeMaScore: A new evaluation metric for automatic speech recognition tasks
Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
SEQ-former: A context-enhanced and efficient automatic speech recognition framework
Sequential Editing for Lifelong Training of Speech Recognition Models
SER Evals: In-domain and Out-of-domain benchmarking for speech emotion recognition
Serialized Output Training by Learned Dominance

« prev Page 16/21 next »