8 papers
SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning
KiHyun Nam, Jungwoo Heo, Siu Bae +2
As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-sp…
SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compression in Speaker Verification
Jungwoo Heo, Hyun-seo Shin, Chan-yeong Lim +4
Self-supervised learning (SSL) has pushed speaker verification accuracy close to state-of-the-art levels, but the Transformer backbones used in most SSL encoders hinder on-device a…
Token-based Attractors and Cross-attention in Spoof Diarization
Kyo-Won Koo, Chan-yeong Lim, Jee-weon Jung +2
Spoof diarization identifies ``what spoofed when" in a given speech by temporally locating spoofed regions and determining their manipulation techniques. As a first step toward thi…
SEED: Speaker Embedding Enhancement Diffusion Model
KiHyun Nam, Jungwoo Heo, Jee-weon Jung +4
A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based…
MR-RawNet: Speaker verification system with multiple temporal resolutions for variable duration utterances using raw waveforms
Seung-bin Kim, Chan-yeong Lim, Jungwoo Heo +4
In speaker verification systems, the utilization of short utterances presents a persistent challenge, leading to performance degradation primarily due to insufficient phonetic info…
HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods
Hyun-seo Shin, Jungwoo Heo, Ju-ho Kim +3
Audio deepfake detection (ADD) is the task of detecting spoofing attacks generated by text-to-speech or voice conversion systems. Spoofing evidence, which helps to distinguish betw…
Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models
Ju-ho Kim, Jungwoo Heo, Hyun-seo Shin +2
Background noise considerably reduces the accuracy and reliability of speaker verification (SV) systems. These challenges can be addressed using a speech enhancement system as a fr…
One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification
Jungwoo Heo, Chan-yeong Lim, Ju-ho Kim +2
The application of speech self-supervised learning (SSL) models has achieved remarkable performance in speaker verification (SV). However, there is a computational cost hurdle in e…