Slt 2024

117 papers

Top Research Directions

Research directions most represented by Slt 2024 papers.

Performance Scaling Through Massive Acoustic Datasets 2
Efficient Neural Architectures for Real-Time Speech Synthesis 2
Mitigating Data Scarcity in Affective Speech Models 2
The Performance Ceiling of Pre-trained Feature Dependency 1
Deep Representation Learning for Robust Speech Emotion Recognition 1
Token Importance Weighting for Language Model Optimization 1
Zero-Shot Reranking with Large Language Models 1
Array Agnostic Multi Channel Speech Processing 1
The Clean Signal Penalty in Robust Speech Models 1
Generative Error Correction for Automatic Speech Recognition 1
Generative Error Correction for Speech Recognition 1
Flat Loss Landscapes for Robust Neural Network Quantization 1
Consolidating Multi-Stage Speech Pipelines into End-to-End Networks 1
Probabilistic Latent Spaces for Modeling Speech Prosody 1
Scaling Generative Audio Models to High Sampling Rates 1

Top Authors

AuthorPapers
Shinji Watanabe10
Hung-yi Lee8
Haibin Wu7
Peter Bell6
Yanmin Qian6
Shuai Wang5
Yu Tsao5
Zhen-Hua Ling5
Haizhou Li4
Kong Aik Lee4
Yi-Cheng Lin4
Zhizheng Wu4
Catherine Lai3
Chao-Han Huck Yang3
Chao Zhang3
Chih-Kai Yang3
Dongchao Yang3
Dong Yu3
EngSiong Chng3
Hainan Xu3

Impactful Papers

Papers from Slt 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Spoofing-Aware Speaker Verification Robust Against Domain and Channel Mismatches
SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model
Stage-Wise and Prior-Aware Neural Speech Phase Prediction
Stutter-Solver: End-To-End Multi-Lingual Dysfluency Detection
Summary of Low-Resource Dysarthria Wake-Up Word Spotting Challenge
SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge
SWIM: Short-Window CNN Integrated With Mamba for EEG-Based Auditory Spatial Attention Decoding
The 2nd Futuredial Challenge: Dialog Systems With Retrieval Augmented Generation (Futuredial-RAG)
The T05 System for the voicemos challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech
The Voicemos Challenge 2024: Beyond Speech Quality Prediction
Token-Weighted RNN-T For Learning From Flawed Data
Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing
Training Large ASR Encoders With Differential Privacy
TTSDS - Text-to-Speech Distribution Score
Visinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation
WHISMA: A Speech-LLM to Perform Zero-Shot Spoken Language Understanding
Zero-Shot Audio Topic Reranking Using Large Language Models

« prev Page 3/3