Publications

I'd like to explain about the research I've been get in touch with.

Efficiency

• Segment-Level Vectorized Beam Search Based on Partially Autoregressive Inference: This proposes a decoding process that combines the autoregressive and non-autoregressive process. We improved trade-off between accuracy and inference speed.

• Context-aware Dynamic Pruning for Speech Foundation Models

• On-device Streaming Discrete Speech Units

• Context-Driven Dynamic Pruning for Large Speech Foundation Models

Systems

• ESPnet-ONNX: Bridging a Gap Between Research and Production: A software to convert pre-trained model of ESPnet into ONNX.

• ESPnet-EZ: Python-Only ESPnet For Easy Fine-Tuning And Integration

Co-authord

• A Comparative Study on Transformer vs RNN in Speech Applications: The comparison of RNN based models and Transformer based models on Speech to text task.

• Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages