Latest Research in Audio and Speech Processing

Top Research Topics in Audio and Speech Processing

• Audio and Speech Processing — 40 papers
• Computation and Language — 32 papers
• Sound — 32 papers
• Speech Recognition and Synthesis — 10 papers
• Speech and Audio Processing — 5 papers
• Computer Vision and Pattern Recognition — 4 papers
• Machine Learning — 3 papers
• Artificial Intelligence — 3 papers
• Mobile and Web Applications — 3 papers
• Speech and dialogue systems — 2 papers

Highest-Cited Papers

1. DELTA-TTS: Adapting Autoregressive Model into Diffusion Language Model for Text-to-Speech
2. Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders
3. Adapting Large-Scale Foundation Models for Turkic Speech-to-Speech Translation: Fine-Tuned Cascade and Direct Approaches
4. The Eloquence team submission for task 1 of MLC-SLM challenge
5. Speaker Verification Under Real Classroom Conditions for English Speech
6. GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
7. Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio Infilling
8. MeloCodec: Harnessing Melodic Priors for High-Fidelity Singing Voice Representation
9. Deep Learning for Real-Time Sound Order Recognition in Human-Robot Interaction
10. The Role of Disfluencies in Speech Translation
11. Analyzing Speech Condition Effects in Dysarthric ASR: A Layer-wise Probing Study
12. AST: Adaptive, Seamless, and Training-Free Precise Speech Editing
13. Open Kalenjin Automatic Speech Recognition: Adapting Parakeet-TDT to a Low-Resource Nilotic Language
14. Open Kalenjin Automatic Speech Recognition: Adapting Parakeet-TDT to a Low-Resource Nilotic Language
15. Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval
16. Adaptive Perturbation Selection for Contrastive Audio Decoding
17. Latent Softmax for Data-Efficient Phoneme-Based Multilingual ASR Across Tonal and Non-Tonal Languages
18. Improving ASR Fairness for Cleft Lip and Palate Speech: A Study on Severity-Aware Data Mixing
19. Zero-Latency Client-Side Audio Vocal Separation via Stereo Phase Subtraction and Formant Notch Filter Banks
20. Zero-Latency Client-Side Audio Vocal Separation via Stereo Phase Subtraction and Formant Notch Filter Banks