Fastspeech 2: Fast and high-quality end-to-end text to speech
Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech
significantly faster than previous autoregressive models with comparable quality. The …
significantly faster than previous autoregressive models with comparable quality. The …
Fastspeech: Fast, robust and controllable text to speech
Neural network based end-to-end text to speech (TTS) has significantly improved the quality
of synthesized speech. Prominent methods (eg, Tacotron 2) usually first generate mel-…
of synthesized speech. Prominent methods (eg, Tacotron 2) usually first generate mel-…
[PDF][PDF] Single-cell transcriptomics reveals a population of dormant neural stem cells that become activated upon brain injury
E Llorens-Bobadilla, S Zhao, A Baser, G Saiz-Castro… - Cell stem cell, 2015 - cell.com
Heterogeneous pools of adult neural stem cells (NSCs) contribute to brain maintenance
and regeneration after injury. The balance of NSC activation and quiescence, as well as the …
and regeneration after injury. The balance of NSC activation and quiescence, as well as the …
Comprehensive algorithm for quantitative real-time polymerase chain reaction
S Zhao, RD Fernald - Journal of computational biology, 2005 - liebertpub.com
Quantitative real-time polymerase chain reactions (qRT-PCR) have become the method of
choice for rapid, sensitive, quantitative comparison of RNA transcript abundance. Useful data …
choice for rapid, sensitive, quantitative comparison of RNA transcript abundance. Useful data …
Layered graphene/quantum dots for photovoltaic devices
Layering in the sun: Layered graphene and quantum dot (QD) films can be fabricated simply
on transparent conducting indium tin oxide (ITO) substrates from aqueous solutions. The …
on transparent conducting indium tin oxide (ITO) substrates from aqueous solutions. The …
Neural codec language models are zero-shot text to speech synthesizers
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically,
we train a neural codec language model (called Vall-E) using discrete codes derived from …
we train a neural codec language model (called Vall-E) using discrete codes derived from …
[HTML][HTML] Rapid complete reconfiguration induced actual active species for industrial hydrogen evolution reaction
Rational regulation of electrochemical reconfiguration and exploration of activity origin are
important foundations for realizing the optimization of electrocatalyst activity, but rather …
important foundations for realizing the optimization of electrocatalyst activity, but rather …
Neural speech synthesis with transformer network
Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are
proposed and achieve state-of-theart performance, they still suffer from two problems: 1) low …
proposed and achieve state-of-theart performance, they still suffer from two problems: 1) low …
A unique approach to development of near-infrared fluorescent sensors for in vivo imaging
Near-infrared (NIR) fluorescent sensors have emerged as promising molecular tools for
imaging biomolecules in living systems. However, NIR fluorescent sensors are very challenging …
imaging biomolecules in living systems. However, NIR fluorescent sensors are very challenging …
[HTML][HTML] Associations between COVID-19 misinformation exposure and belief with COVID-19 knowledge and preventive behaviors: cross-sectional online study
Background Online misinformation proliferation during the COVID-19 pandemic has become
a major public health concern. Objective We aimed to assess the prevalence of COVID-19 …
a major public health concern. Objective We aimed to assess the prevalence of COVID-19 …