Latest Research in Conversational Speech Processing

Top Research Topics in Conversational Speech Processing

• Audio and Speech Processing — 110 papers
• Sound — 97 papers
• Computation and Language — 74 papers
• Speech Recognition and Synthesis — 24 papers
• Machine Learning — 11 papers
• Artificial Intelligence — 7 papers
• Natural Language Processing Techniques — 5 papers
• Emotion and Mood Recognition — 5 papers
• Computer Vision and Pattern Recognition — 5 papers
• Phonetics and Phonology Research — 5 papers

Highest-Cited Papers

1. DOTA-ME-CS: daily oriented text audio-Mandarin English-Code switching dataset (1 citations)
2. Towards inclusive voice biometrics: Dysarthria-discriminative embeddings for ASV system
3. Speech intelligibility comparison of standalone and two-stage deep learning architectures for behind-the-ear-to-binaural enhancement
4. A2SSC: An Agent-based Adaptive Semantic Speech Communication System
5. DESED and DataSED precomputed caches for Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
6. Enabling automatic transcription of child-centered audio recordings from real-world environments
7. Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain
8. Foreground Voice Activity Detection: Learning Speaker Selectivity from Supervision
9. Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification
10. CircleMatch: Prototype Matching with Circular Temporal Statistics for Tiny Keyword Spotting
11. Multimodal Conversational Context for LLM-Based ASR: Data Construction, Training, and Benchmark
12. Can Large Audio Language Models Ignore Multilingual Distractors? An Evaluation of Their Selective Auditory Attention Capabilities
13. Alignment-Path Distillation from Non-streaming ASR-LLMs for Streaming Speech Recognition
14. Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
15. Scaling Audio Models Efficiently: Joint Optimization of Scale, Resolution, Adaptation, Precision, and Sparsity
16. Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation
17. Soft Posterior Speaker Injection for Multi-Talker Speech Recognition
18. Design of the IBM Granite 5.0 TurboCTC ASR Model
19. Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis
20. Beyond the Stability--Plasticity Frontier in Streaming Target Speaker Extraction

Sub-Regions

• Computation and Language — 127 papers
• Sound — 81 papers
• Speech Recognition and Synthesis — 54 papers
• Audio and Speech Processing — 35 papers
• Natural Language Processing Techniques — 27 papers
• Phonetics and Phonology Research — 22 papers