Latest Research in Sound
25 research papers · 2026 median publication year
Top Research Topics in Sound
- Sound — 7 papers
- Emotion and Mood Recognition — 7 papers
- Computation and Language — 5 papers
- Audio and Speech Processing — 3 papers
- Machine Learning — 1 papers
- Speech Recognition and Synthesis — 1 papers
- Authorship Attribution and Profiling — 1 papers
Highest-Cited Papers
- Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis
- AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition
- Advances in speech emotion recognition using a CNN and gender-based segmentation framework with feature selection techniques
- EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis
- Looking for Affect in Spontaneous Finnish Speech through Linguistic Interpretability
- A Novel Hybrid Deep Learning Technique for Speech Emotion Detection using Feature Engineering
- The False Resonance: A Critical Examination of Emotion Embedding Similarity for Speech Generation Evaluation
- Harness TTS: Towards Context-Aware Expressive Speech Synthesis with Harness Layer
- Explainable Lightweight Compact Deep Models for Speech Emotion Recognition
- AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis
- TinyML-Based Speech Emotion Recognition on Microcontrollers Using Quantized CNNs and Mel-Filterbank Energy Features
- Dialogs: a studio-quality expressive conversational Russian speech corpus for dialog assistants
- Emotion Recognition Using Acoustic Features and Deep Learning: A Speaker-Independent Study
- Speaker recognition under whispered and object-in-mouth voice disguise method using hybrid feature extraction and machine learning technique
- SHAP-Guided explainable feature selection for efficient dialect classification
- Enhancing children’s emotional education with speech emotion recognition using deep learning
- Study of gender-specific emotion expressivity in speech using MFCC and CNN
- SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
- TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
- TRACE-EVC: Text-Guided Relative Affective Control for Zero-Shot Emotional Voice Conversion