25 citations · 49 across the 17 of their papers we have counts for
5 papers · 1 filter
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…