Hiroki Kanagawa

5 papers · 2020–2024 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

Interspeech (5)

Top co-authors

Yusuke Ijima (5) Takafumi Moriya (2) Hiroyuki Toda (1)

Research topics

Machine Learning (4) Deep Learning (3) Application Areas (3) Architectures (3) Core Methods (2) Mathematics & Optimization (1) Speech & Audio (1) Learning Types (1) Mathematics (1) Models (1) Optimization & Theory (1) Recognition (1) Synthesis (1) Techniques (1)

Keywords

speech synthesis (3) neural vocoder (2) neural transducer (2) voice conversion (2) cpu inference (1) neural codec (1) discrete speech unit (1) waveform generation (1) self-supervised representation learning (1) linear predictive coding (1) streaming voice conversion (1) alignment-free training (1) subband signal (1) model compression (1) multi-sample prediction (1) multivariate gaussian (1) knowledge distillation (1) tensor decomposition (1)

Papers

Knowledge Distillation from Self-Supervised Representation Learning Model with Discrete Speech Units for Any-to-Any Streaming Voice Conversion Interspeech 2024 Pre-training Neural Transducer-based Streaming Voice Conversion for Faster Convergence and Alignment-free Training Interspeech 2024 VC-T: Streaming Voice Conversion Based on Neural Transducer Interspeech 2023 Joint Modeling of Multi-Sample and Subband Signals for Fast Neural Vocoding on CPU Interspeech 2022 Lightweight LPCNet-Based Neural Vocoder with Tensor Decomposition Interspeech 2020