Sangjin Kim

4 papers · 2018–2025 · 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 (12)

Venues

Interspeech (2) EMNLP (1) ICML (1)

Top co-authors

Beomjeong Kim (2) Jungil Kong (2) Jeongmin Kim (2) Dohee Kong (2) Jihoon Park (2) Seojin Lee (1) Injee Song (1) Seokyoung Hong (1) Sohee Park (1) Wonbeom Jang (1)

Research topics

Speech & Audio (3) Synthesis (3) Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Core AI (2) Learning Types · Machine Learning (2) Natural Language Processing (1) Architectures (1) Generation (1) Learning Types · Deep Learning (1) Models (1)

Keywords

transformer architecture (1) benchmark evaluation (1) adversarial learning (1) speech synthesis (1) end-to-end learning (1) tool use (1) retrieval-augmented generation (1) singing voice synthesis (1) reasoning capability (1) text-to-speech synthesis (1) agent system (1) llm agent (1) speech naturalness (1) lstm recurrent neural network (1) large language model (1) neural network (1) zero-shot method (1) feature composition (1) domain-specific benchmark (1) korean language synthesis (1)

Papers

TelAgentBench: A Multi-faceted Benchmark for Evaluating LLM-based Agents in Telecommunications EMNLP 2025 ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis ICML 2024 VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design Interspeech 2023 Korean Singing Voice Synthesis Based on an LSTM Recurrent Neural Network Interspeech 2018