17 citations · 65 across the 38 of their papers we have counts for
9 papers · 1 filter
Robot Confirmation Generation and Action Planning Using Long-context Q-Former Integrated with Multimodal LLM
Chiori Hori, Yoshiki Masuyama, Siddarth Jain +4
Human-robot collaboration towards a shared goal requires robots to understand human action and interaction with the surrounding environment. This paper focuses on human-robot inter…
SUNAC: Source-aware Unified Neural Audio Codec
Ryo Aihara, Yoshiki Masuyama, Francesco Paissan +3
Neural audio codecs (NACs) provide compact representations that can be leveraged in many downstream applications, in particular large language models. Yet most NACs encode mixtures…
Physics-Informed Direction-Aware Neural Acoustic Fields
Yoshiki Masuyama, François G. Germain, Gordon Wichern +2
This paper presents a physics-informed neural network (PINN) for modeling first-order Ambisonic (FOA) room impulse responses (RIRs). PINNs have demonstrated promising performance i…
Factorized RVQ-GAN For Disentangled Speech Tokenization
Sameer Khurana, Dominik Klement, Antoine Laurent +13
We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single…
HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement
Amir Hussein, Sameer Khurana, Gordon Wichern +2
Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches str…
Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses
Christopher Ick, Gordon Wichern, Yoshiki Masuyama +2
The characteristics of a sound field are intrinsically linked to the geometric and spatial properties of the environment surrounding a sound source and a listener. The physics of s…
Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training
Christopher Ick, Gordon Wichern, Yoshiki Masuyama +2
This report details MERL's system for room impulse response (RIR) estimation submitted to the Generative Data Augmentation Workshop at ICASSP 2025 for Augmenting RIR Data (Task 1)…
Handling Domain Shifts for Anomalous Sound Detection: A Review of DCASE-Related Work
Kevin Wilkinghoff, Takuya Fujimura, Keisuke Imoto +3
When detecting anomalous sounds in complex environments, one of the main difficulties is that trained models must be sensitive to subtle differences in monitored target signals, wh…
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization
Yoshiki Masuyama, Gordon Wichern, François G. Germain +2
Head-related transfer functions (HRTFs) with dense spatial grids are desired for immersive binaural audio generation, but their recording is time-consuming. Although HRTF spatial u…