activity
20242026
collaborators

8 papers

eess.AS2026

Cached LLM Probability Retrieval for Speech Recognition

Sheng Li, Takahiro Shinozaki, Tatsuya Kawahara

Large language models (LLMs) enhance automatic speech recognition (ASR) by providing linguistic priors; however, their direct rescoring is costly because it requires evaluating eve…

cs.SD2026

MemNMF: Memory-Augmented NMF on LPC Spectra for Anomalous Sound Detection

Phurich Saengthong, Takahiro Shinozaki

Autoencoder-based anomalous sound detection is attractive for machine condition monitoring because it can be trained using only normal recordings and yields an interpretable anomal…

eess.AS2026

Synchronized Three-Dimensional Vocal-Tract Motion for Speech Synchronization via Joint-Embedding Predictive Architecture Alignment

Sheng Li, Takahiro Shinozaki

Modern neural speech systems can generate intelligible waveforms, but they usually hide the physical speech-production state that produced the sound. Conversely, biomechanical voca…

cs.SD2026

Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection

Phurich Saengthong, Takahiro Shinozaki

Detecting subtle deviations in noisy acoustic environments is central to anomalous sound detection (ASD). A common training-free ASD pipeline temporally pools frame-level represent…

cs.SD2025

Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement

Jianing Yang, Sheng Li, Takahiro Shinozaki +2

Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details…

eess.AS2025

RAG-Boost: Retrieval-Augmented Generation Enhanced LLM-based Speech Recognition

Pengcheng Wang, Sheng Li, Takahiro Shinozaki

In this paper, we propose RAG-Boost (ST-ShinozakiLab Task I system), which enhances the baseline LLM-based ASR system of the MLC-SLM Challenge (task I) with a retrieval-augmented g…