Latest Research in Speech Recognition and Synthesis
51 research papers · 2026 median publication year
Top Research Topics in Speech Recognition and Synthesis
- Sound — 18 papers
- Audio and Speech Processing — 17 papers
- Computation and Language — 8 papers
- Speech Recognition and Synthesis — 2 papers
- Computer Vision and Pattern Recognition — 2 papers
- Artificial Intelligence — 1 papers
- Speech and Audio Processing — 1 papers
- Machine Learning — 1 papers
- Multimedia — 1 papers
Highest-Cited Papers
- Unfolded Recursive Expectation-Maximization Neural Network For Speaker Tracking
- VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment
- Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens
- LL-SDR: Low-Latency Speech enhancement through Discrete Representations
- MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
- Improving Zero-Shot Phonetic Classification through Language-Agnostic Articulatory Features
- A lightweight hybrid 2D–1D depthwise-separable CNN with frequency-only pooling for efficient small-footprint keyword spotting
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
- SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
- StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis
- FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis
- AM-DANet: Additive margin with dynamic augmentation network for speaker identification
- Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
- LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement
- ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
- Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
- Investigating the Integration of Spatial Information in Foundation-Model-Based Speaker Diarization
- Teaching Speech Enhancement Models to Sing: Domain Adaptation from Speech Enhancement to Singing Voice Separation
- Synchronized Three-Dimensional Vocal-Tract Motion for Speech Synchronization via Joint-Embedding Predictive Architecture Alignment