15 papers
Beyond Fixed Targets: On-Policy One-Shot Speaker Personalization for Autoregressive Text-To-Speech Models
Sangkwon Park, Che Hyun Lee, Heeseung Kim +1
One-shot personalization of autoregressive (AR) text-to-speech (TTS) models remains challenging because supervised fine-tuning (SFT) on a single reference pair rapidly degrades gen…
LILAC: An Idempotent Neural Speech Codec
June Young Yi, Dongwook Lee, Jiheum Yeom +1
Neural Audio Codecs are widely adopted in speech generation and editing. However, existing neural audio codecs are not idempotent: across the paper's twelve baseline systems, every…
Learning When to Reason for Text-to-SQL via SFT and DPO
Soohyuk Jang, Jiheum Yeom, Nohil Park +4
Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inferen…
TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment
Kanghyun Baek, Sangyub Lee, Jin Young Choi +6
Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement met…
DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy
Jaewoo Song, Jooyoung Choi, Kanghyun Baek +3
Despite recent text-to-image models achieving highfidelity text rendering, they still struggle with long or multiple texts due to diluted global attention. We propose DCText, a tra…
Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation
Chaehun Shin, Jooyoung Choi, Johan Barthelemy +2
We present Subject Fidelity Optimization (SFO), a novel comparative learning framework for zero-shot subject-driven generation that enhances subject fidelity. Existing supervised f…
EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models
Che Hyun Lee, Heeseung Kim, Jiheum Yeom +1
We propose EdiText, a controllable text editing method that modifies the reference text to desired attributes at various scales. We integrate an SDEdit-based editing technique that…
Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models
Heeseung Kim, Che Hyun Lee, Sangkwon Park +4
Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances…
CNN-based TEM image denoising from first principles
Jinwoong Chae, Sungwook Hong, Sungkyu Kim +2
Transmission electron microscope (TEM) images are often corrupted by noise, hindering their interpretation. To address this issue, we propose a deep learning-based approach using s…
Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation
Yongsung Kim, Minjun Park, Jooyoung Choi +1
Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction. However, directly applying 3D Gaussian Splatting (3D…
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Chaehun Shin, Jooyoung Choi, Heeseung Kim +1
Subject-driven text-to-image generation aims to produce images of a new subject within a desired context by accurately capturing both the visual characteristics of the subject and…
Style-Friendly SNR Sampler for Style-Driven Generation
Jooyoung Choi, Chaehun Shin, Yeongtak Oh +3
Recent text-to-image diffusion models generate high-quality images but struggle to learn new, personalized styles, which limits the creation of unique style templates. In style-dri…
NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers
Nohil Park, Heeseung Kim, Che Hyun Lee +3
We present NanoVoice, a personalized text-to-speech model that efficiently constructs voice adapters for multiple speakers simultaneously. NanoVoice introduces a batch-wise speaker…
VoiceGuider: Enhancing Out-of-Domain Performance in Parameter-Efficient Speaker-Adaptive Text-to-Speech via Autoguidance
Jiheum Yeom, Heeseung Kim, Jooyoung Choi +3
When applying parameter-efficient finetuning via LoRA onto speaker adaptive text-to-speech models, adaptation performance may decline compared to full-finetuned counterparts, espec…
VoiceTailor: Lightweight Plug-In Adapter for Diffusion-Based Personalized Text-to-Speech
Heeseung Kim, Sang-gil Lee, Jiheum Yeom +3
We propose VoiceTailor, a parameter-efficient speaker-adaptive text-to-speech (TTS) system, by equipping a pre-trained diffusion-based TTS model with a personalized adapter. VoiceT…