25 citations · 49 across the 17 of their papers we have counts for
17 papers
ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching
Jihwan Kim, Nam Soo Kim
Zero-shot dialog TTS benefits from flow-matching, but minute-scale generation on dense mel-spectrograms causes severe memory bottlenecks, often forcing unnatural chunked synthesis.…
Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition
Hyeonseung Lee, Ji Won Yoon, Sungsoo Kim +1
Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and…
Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction
Minchan Kim, Myeonghun Jeong, Byoung Jin Choi +2
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a ne…
EM-Network: Oracle Guided Self-distillation for Sequence Learning
Ji Won Yoon, Sunghwan Ahn, Hyeonseung Lee +3
We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to con…
MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization
Ji Won Yoon, Seok Min Kim, Nam Soo Kim
Self-supervised learning (SSL) has shown significant progress in speech processing tasks. However, despite the intrinsic randomness in the Transformer structure, such as dropout va…
Towards single integrated spoofing-aware speaker verification embeddings
Sung Hwan Mun, Hye-jin Shim, Hemlata Tak +12
This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well a…
When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus
Won Ik Cho, Yoon Kyung Lee, Seoyeon Bae +5
Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept. Such a tendency can be see…
SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
Byoung Jin Choi, Myeonghun Jeong, Joun Yeop Lee +1
Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker. The main challenge of ZSM-TTS is to incr…
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition
Ji Won Yoon, Beom Jun Woo, Sunghwan Ahn +2
Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promi…
Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech
Byoung Jin Choi, Myeonghun Jeong, Minchan Kim +2
Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios wit…
Fully Unsupervised Training of Few-shot Keyword Spotting
Dongjune Lee, Minchan Kim, Sung Hwan Mun +2
For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keyw…
Disentangled Speaker Representation Learning via Mutual Information Minimization
Sung Hwan Mun, Min Hyun Han, Minchan Kim +2
Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unrave…
HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition
Ji Won Yoon, Beom Jun Woo, Nam Soo Kim
Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in automatic speech recognition (ASR). However, th…
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification
Sung Hwan Mun, Jee-weon Jung, Min Hyun Han +1
The majority of recent state-of-the-art speaker verification architectures adopt multi-scale processing and frequency-channel attention mechanisms. Convolutional layers of these mo…
Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
Minchan Kim, Myeonghun Jeong, Byoung Jin Choi +3
Training a text-to-speech (TTS) model requires a large scale text labeled speech corpus, which is troublesome to collect. In this paper, we propose a transfer learning framework fo…
Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
Sung Hwan Mun, Min Hyun Han, Dongjune Lee +2
In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and…
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models
Ji Won Yoon, Hyung Yong Kim, Hyeonseung Lee +2
Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (st…