Min-Jae Hwang

9 papers · 2018–2024 · 3 venues · 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🔥 Unstoppable · Bronze

Venues

Interspeech (7) ACL (1) NeurIPS (1)

Top co-authors

Eunwoo Song (7) Jae-Min Kim (4) Ryuichi Yamamoto (4) Ohsung Kwon (3) Hong-Goo Kang (3) Jin-Seob Kim (3) Hyun-Wook Yoon (2) Sang-Hoon Lee (1) Seung-Bin Kim (1) Peng-Jen Chen (1)

Research topics

Deep Learning (8) Speech & Audio (7) Synthesis (7) Machine Learning (6) Models (6) Learning Types · Machine Learning (4) Application Areas (2) Learning Types · Deep Learning (2) Techniques (2) Artificial Intelligence (1) Analysis (1) Architectures (1) Core AI (1) Core Methods (1)

Keywords

speech synthesis (6) neural vocoder (2) self-supervised learning (2) text-to-speech synthesis (2) variational autoencoder (2) waveform generation (2) noise modeling (1) language model (1) speech enhancement (1) support vector machine (1) generative model (1) deep learning (1) generative adversarial network (1) noise robustness (1) latent feature (1) speech-to-speech translation (1) generative pre-trained transformer (1) acoustic model (1) latent space embedding (1) prosody analysis (1)

Papers

Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation ACL 2024 HierSpeech: Bridging the Gap between Text and Speech by Hierarchical Variational Inference using Self-supervised Representations for Speech Synthesis NeurIPS 2022 Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems Interspeech 2022 TTS-by-TTS 2: Data-Selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder Interspeech 2022 High-Fidelity Parallel WaveGAN with Multi-Band Harmonic-Plus-Noise Model Interspeech 2021 LiteTTS: A Lightweight Mel-Spectrogram-Free Text-to-Wave Synthesizer Based on Generative Adversarial Networks Interspeech 2021 Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder Interspeech 2020 Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment Interspeech 2019 A Unified Framework for the Generation of Glottal Signals in Deep Learning-based Parametric Speech Synthesis Systems Interspeech 2018