Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Mun, Seongkyu"'
Autor:
Ahn, Junseok, Kim, Youkyum, Choi, Yeunju, Kwak, Doyeop, Kim, Ji-Hoon, Mun, Seongkyu, Chung, Joon Son
This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice s
Externí odkaz:
http://arxiv.org/abs/2407.18505
Autor:
Bae, Jae-Sung, Lee, Joun Yeop, Lee, Ji-Hyun, Mun, Seongkyu, Kang, Taehwa, Cho, Hoon-Young, Kim, Chanwoo
Previous works in zero-shot text-to-speech (ZS-TTS) have attempted to enhance its systems by enlarging the training data through crowd-sourcing or augmenting existing speech data. However, the use of low-quality data has led to a decline in the overa
Externí odkaz:
http://arxiv.org/abs/2310.03538
Autor:
Lee, Jihwan, Bae, Jae-Sung, Mun, Seongkyu, Choi, Heejin, Lee, Joun Yeop, Cho, Hoon-Young, Kim, Chanwoo
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 such cross-lingual TTS systems is troublesome. The vowel space analysis,
Externí odkaz:
http://arxiv.org/abs/2211.03078
Autor:
Lee, Jihwan, Lee, Joun Yeop, Choi, Heejin, Mun, Seongkyu, Park, Sangjun, Bae, Jae-Sung, Kim, Chanwoo
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 problem, we propose a novel, intuitive method to synthesize speech in diffe
Externí odkaz:
http://arxiv.org/abs/2204.01271
In this paper, we present a streaming end-to-end speech recognition model based on Monotonic Chunkwise Attention (MoCha) jointly trained with enhancement layers. Even though the MoCha attention enables streaming speech recognition with recognition ac
Externí odkaz:
http://arxiv.org/abs/2105.01254
This paper addresses the noisy label issue in audio event detection (AED) by refining strong labels as sequential labels with inaccurate timestamps removed. In AED, strong labels contain the occurrence of a specific event and its timestamps correspon
Externí odkaz:
http://arxiv.org/abs/2007.05191
The goal of this work is to train effective representations for keyword spotting via metric learning. Most existing works address keyword spotting as a closed-set classification problem, where both target and non-target keywords are predefined. There
Externí odkaz:
http://arxiv.org/abs/2005.08776
Autor:
Chung, Joon Son, Huh, Jaesung, Mun, Seongkyu, Lee, Minjae, Heo, Hee Soo, Choe, Soyeon, Ham, Chiheon, Jung, Sunghwan, Lee, Bong-Jin, Han, Icksang
The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level representation that has small intra-speaker and large inter-speaker distanc
Externí odkaz:
http://arxiv.org/abs/2003.11982
Content and style representations have been widely studied in the field of style transfer. In this paper, we propose a new loss function using speaker content representation for audio source separation, and we call it speaker representation loss. The
Externí odkaz:
http://arxiv.org/abs/1911.02411
Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful architectures or lo
Externí odkaz:
http://arxiv.org/abs/1910.11238