Zobrazeno 1 - 10
of 174
pro vyhledávání: '"Gao, Xiaoxue"'
Text-to-speech (TTS) has been extensively studied for generating high-quality speech with textual inputs, playing a crucial role in various real-time applications. For real-world deployment, ensuring stable and timely generation in TTS models against
Externí odkaz:
http://arxiv.org/abs/2407.01927
Audio-visual active speaker detection (AV-ASD) aims to identify which visible face is speaking in a scene with one or more persons. Most existing AV-ASD methods prioritize capturing speech-lip correspondence. However, there is a noticeable gap in add
Externí odkaz:
http://arxiv.org/abs/2404.00861
Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has just start
Externí odkaz:
http://arxiv.org/abs/2402.15725
Autor:
Gao, Xiaoxue, Jiang, Edwin, Pike, Andrew, Lee, Eldred, Wu, Margaret, Wang, Huan, Somers, Sheppard, Li, Weiyang, Hautier, Geoffroy, Baker, Ian, Liu, Jifeng
High entropy alloys (HEAs) have attracted substantial interest in recent years. Thus far, most investigations have focused on their applications as structural materials rather than functional materials. In this paper, we show that FeMnNiAlCr HEAs can
Externí odkaz:
http://arxiv.org/abs/2312.15076
Autor:
Gao, Xiaoxue, Fu, Sidan, Fang, Tao, Yu, Xiaobai, Wang, Haozhe, Ji, Qingqing, Kong, Jing, Wang, Xiaoxin, Liu, Jifeng
2D MoS2 attracts increasing attention for its application in flexible electronics and photonic devices. For 2D material optoelectronic devices, light absorption of the molecularly thin 2D absorber would be one of the key limiting factors in device ef
Externí odkaz:
http://arxiv.org/abs/2301.01164
The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem have not be
Externí odkaz:
http://arxiv.org/abs/2211.10152
Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and
Externí odkaz:
http://arxiv.org/abs/2210.16755
Lyrics transcription of polyphonic music is challenging as the background music affects lyrics intelligibility. Typically, lyrics transcription can be performed by a two-step pipeline, i.e. a singing vocal extraction front end, followed by a lyrics t
Externí odkaz:
http://arxiv.org/abs/2207.07336
Autor:
Gao, Xiaoxue
Since the relational turn, scholars have combated methodological universalism, nationalism, and individualism in researching social-spatial transformations. Yet, when leaving the gaps between the traveling and local epistemic assumptions unattended,
Externí odkaz:
https://library.oapen.org/handle/20.500.12657/48353
Lyrics transcription of polyphonic music is challenging not only because the singing vocals are corrupted by the background music, but also because the background music and the singing style vary across music genres, such as pop, metal, and hip hop,
Externí odkaz:
http://arxiv.org/abs/2204.03307