8 papers
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…
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…
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…
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…
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…
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…