Latest Research in Speech Recognition and Synthesis

Top Research Topics in Speech Recognition and Synthesis

• Audio and Speech Processing — 16 papers
• Computation and Language — 13 papers
• Sound — 12 papers
• Speech Recognition and Synthesis — 7 papers
• Emotion and Mood Recognition — 2 papers
• Artificial Intelligence — 1 papers
• Phonetics and Phonology Research — 1 papers
• Machine Learning — 1 papers
• Computer Vision and Pattern Recognition — 1 papers

Highest-Cited Papers

1. DOTA-ME-CS: daily oriented text audio-Mandarin English-Code switching dataset (1 citations)
2. A2SSC: An Agent-based Adaptive Semantic Speech Communication System
3. Personalized Keyword Spotting for User-Defined Keywords Leveraging Text-Independent Speaker Verification
4. Multimodal Conversational Context for LLM-Based ASR: Data Construction, Training, and Benchmark
5. Self-Distilled Pronunciation and Accent Control for Neural Text-to-Speech
6. VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval
7. A frontend-backend architecture for tool calls in full-duplex speech models
8. Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs
9. SPEAKER ACCENT RECOGNITION USING MACHINE LEARNING
10. SPEAKER ACCENT RECOGNITION USING MACHINE LEARNING
11. Empirical mode decomposition based CNN prediction model for speech emotion classification using Mel scale spectrograms
12. Taming Long-form Text-to-Speech
13. CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection
14. SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages
15. Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage
16. TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion
17. Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech Models
18. Word Timestamps and Speaker Attribution with a Non-Autoregressive LLM
19. Tone on a Budget: A Reference-Free Metric for Lexical Tone in Massively Multilingual Text-to-Speech
20. Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition