Differentiable Duration Refinement Using Internal Division for Non-Autoregressive Text-to-Speech

Efficient Lightweight Speaker Verification With Broadcasting CNN-Transformer and Knowledge Distillation Training of Self-Attention Maps

Enhancing multimodal emotion recognition through ASR error compensation and LLM fine-tuning

Neural ATSM: Fully neural network-based adaptive time-scale modification using sentence-specific dynamic control

Whisper multilingual downstream task tuning using task vectors

Online subloop search via uncertainty quantization for efficient test-time adaptation

Few-shot keyword-incremental learning with total calibration

Efficient speaker embedding extraction using a twofold sliding window algorithm for speaker diarization

Balanced-Wav2Vec: Enhancing stability and robustness of representation learning through sample reweighting techniques

H4C-TTS: Leveraging multi-modal historical context for conversational text-to-speech