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
Preservation, conservation and phonetic study of the voices of Italian poets: A study on the seven years of the VIP archive
Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units
Pre-training Feature Guided Diffusion Model for Speech Enhancement
Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training
Privacy PORCUPINE: Anonymization of Speaker Attributes Using Occurrence Normalization for Space-Filling Vector Quantization
Probing the Feasibility of Multilingual Speaker Anonymization
Production of fricative consonants in French-speaking children with cochlear implants and typical hearing: acoustic and phonological analyses.
Production of phrases by mechanical models of the human vocal tract
Prompting Large Language Models with Audio for General-Purpose Speech Summarization
Prompting Large Language Models with Mispronunciation Detection and Diagnosis Abilities
Prompting Whisper for QA-driven Zero-shot End-to-end Spoken Language Understanding
Prompt Link Multimodal Fusion in Multimodal Sentiment Analysis
Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
Prompt Tuning for Speech Recognition on Unknown Spoken Name Entities
Prosodic marking of syntactic boundaries in Khoekhoe
Prosody-Driven Privacy-Preserving Dementia Detection
Prosody of speech production in latent post-stroke aphasia
PRVAE-VC2: Non-Parallel Voice Conversion by Distillation of Speech Representations
QGAN: Low Footprint Quaternion Neural Vocoder for Speech Synthesis
QHM-GAN: Neural Vocoder based on Quasi-Harmonic Modeling
Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition
QMixCAT: Unsupervised Speech Enhancement Using Quality-guided Signal Mixing and Competitive Alternating Model Training
Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
Quantifying the effect of speech pathology on automatic and human speaker verification
Quantifying the Role of Textual Predictability in Automatic Speech Recognition
Quantifying Unintended Memorization in BEST-RQ ASR Encoders
Quantity-sensitivity affects recall performance of word stress
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
RaD-Net 2: A causal two-stage repairing and denoising speech enhancement network with knowledge distillation and complex axial self-attention
Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting
Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting
Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource Settings
RAST: A Reference-Audio Synchronization Tool for Dubbed Content
RASU: Retrieval Augmented Speech Understanding through Generative Modeling
RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection
Reading Miscue Detection in Primary School through Automatic Speech Recognition
Real-Time Gaze-directed speech enhancement for audio-visual hearing-aids
Real-time scheme for rapid extraction of speaker embeddings in challenging recording conditions
Real-time Speech Summarization for Medical Conversations
Real-world PTSD Recognition: A Cross-corpus and Cross-linguistic Evaluation
Reduce, Reuse, Recycle: Is Perturbed Data Better than Other Language Augmentation for Low Resource Self-Supervised Speech Models
Reducing Speech Distortion and Artifacts for Speech Enhancement by Loss Function
Reference-Free Estimation of the Quality of Clinical Notes Generated from Doctor-Patient Conversations
Refining Self-supervised Learnt Speech Representation using Brain Activations
Reinforcement Learning based Data Augmentation for Noise Robust Speech Emotion Recognition
Reinforcement Learning from Answer Reranking Feedback for Retrieval-Augmented Answer Generation
Relational Proxy Loss for Audio-Text based Keyword Spotting
Reliable dialogue system for facilitating student-counselor communication
RepCNN: Micro-sized, Mighty Models for Wakeword Detection
RepTor: Re-parameterizable Temporal Convolution for Keyword Spotting via Differentiable Kernel Search

« prev Page 15/21 next »