12 citations · 29 across the 20 of their papers we have counts for
21 papers
HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning
Donggyun Kim, Jack Lu, Chanwoo Kim +2
Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with late…
ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detection
Taewoo Kim, Young Han Lee, Nam In Park +1
Audio deepfake detection is commonly formulated as clip-level binary classification of single-domain audio. However, real-world manipulated audio can exhibit mixed authenticity, wh…
Beyond Short Segments : Expanding Speaker Embeddings with Vector Archives
Hyunku Kang, Minkyu Cho, Chanwoo Kim
The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific information. To address this critic…
SISER: Speaker-Invariant Speech Emotion Recognition with Entropy-Based Adversarial Training
Eunseo Choi, Hyunku Kang, Chanwoo Kim
Speech emotion recognition (SER) faces two fundamental challenges: scarcity of labeled data and inter-speaker variability, both of which hinder generalization of emotion recognitio…
Efficient Punctuation Restoration via Weighted Lookahead Scoring Method for Streaming ASR Systems
Sungmook Woo, Hyungu Kang, Chanwoo Kim
Punctuation restoration improves ASR (Automatic Speech Recognition) readability. However streaming ASR requires online decisions with limited future context. In streaming ASR, the…
Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence
Yerin Ryu, Inseop Shin, Chanwoo Kim
Controllable Singing Voice Synthesis (SVS) aims to generate expressive singing voices reflecting user intent. While recent SVS systems achieve high audio quality, most rely on prob…
OleSpeech-IV: A Large-Scale Multispeaker and Multilingual Conversational Speech Dataset with Diverse Topics
Wei Chu, Yuanzhe Dong, Ke Tan +7
OleSpeech-IV dataset is a large-scale multispeaker and multilingual conversational speech dataset with diverse topics. The audio content comes from publicly-available English podca…
HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition
Gio Paik, Yongbeom Kim, Soungmin Lee +2
Despite advances in multilingual automatic speech recognition (ASR), code-switching (CS), the mixing of languages within an utterance common in daily speech, remains a severely und…
HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning
Donggyun Kim, Chanwoo Kim, Seunghoon Hong
While test-time fine-tuning is beneficial in few-shot learning, the need for multiple backpropagation steps can be prohibitively expensive in real-time or low-resource scenarios. T…
AV-Surf: Surface-Enhanced Geometry-Aware Novel-View Acoustic Synthesis
Hadam Baek, Hannie Shin, Jiyoung Seo +4
Accurately modeling sound propagation with complex real-world environments is essential for Novel View Acoustic Synthesis (NVAS). While previous studies have leveraged visual perce…
HyperCLOVA X Technical Report
Kang Min Yoo, Jaegeun Han, Sookyo In +393
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. H…
Data-driven grapheme-to-phoneme representations for a lexicon-free text-to-speech
Abhinav Garg, Jiyeon Kim, Sushil Khyalia +2
Grapheme-to-Phoneme (G2P) is an essential first step in any modern, high-quality Text-to-Speech (TTS) system. Most of the current G2P systems rely on carefully hand-crafted lexicon…
On the compression of shallow non-causal ASR models using knowledge distillation and tied-and-reduced decoder for low-latency on-device speech recognition
Nagaraj Adiga, Jinhwan Park, Chintigari Shiva Kumar +4
Recently, the cascaded two-pass architecture has emerged as a strong contender for on-device automatic speech recognition (ASR). A cascade of causal and shallow non-causal encoders…
Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
Eunseop Yoon, Hee Suk Yoon, Dhananjaya Gowda +7
Text-to-Text Transfer Transformer (T5) has recently been considered for the Grapheme-to-Phoneme (G2P) transduction. As a follow-up, a tokenizer-free byte-level model based on T5 re…
An Empirical Study on L2 Accents of Cross-lingual Text-to-Speech Systems via Vowel Space
Jihwan Lee, Jae-Sung Bae, Seongkyu Mun +4
With the recent developments in cross-lingual Text-to-Speech (TTS) systems, L2 (second-language, or foreign) accent problems arise. Moreover, running a subjective evaluation for su…
Contrastive Corpus Attribution for Explaining Representations
Chris Lin, Hugh Chen, Chanwoo Kim +1
Despite the widespread use of unsupervised models, very few methods are designed to explain them. Most explanation methods explain a scalar model output. However, unsupervised mode…
Learning to Estimate Shapley Values with Vision Transformers
Ian Covert, Chanwoo Kim, Su-In Lee
Transformers have become a default architecture in computer vision, but understanding what drives their predictions remains a challenging problem. Current explanation approaches re…
Into-TTS : Intonation Template Based Prosody Control System
Jihwan Lee, Joun Yeop Lee, Heejin Choi +4
Intonations play an important role in delivering the intention of a speaker. However, current end-to-end TTS systems often fail to model proper intonations. To alleviate this probl…
Two-Pass End-to-End ASR Model Compression
Nauman Dawalatabad, Tushar Vatsal, Ashutosh Gupta +4
Speech recognition on smart devices is challenging owing to the small memory footprint. Hence small size ASR models are desirable. With the use of popular transducer-based models,…
Semi-supervised transfer learning for language expansion of end-to-end speech recognition models to low-resource languages
Jiyeon Kim, Mehul Kumar, Dhananjaya Gowda +2
In this paper, we propose a three-stage training methodology to improve the speech recognition accuracy of low-resource languages. We explore and propose an effective combination o…
Decision Attentive Regularization to Improve Simultaneous Speech Translation Systems
Mohd Abbas Zaidi, Beomseok Lee, Sangha Kim +1
Simultaneous translation systems start producing the output while processing the partial source sentence in the incoming input stream. These systems need to decide when to read mor…