#zhang chuchu

[silylilyanimove]

[justanie]

I've been so involved in going back to school that I can barely focus on my drawing planned for these dates...in the meantime I'll leave this old drawing from 2021!!

[waffulaa]

VOCALOID4 Zhang Chuchu reference sheet.

[vocaloidfactoftheday]

Zhang Chuchu's voicebank has been preserved and uploaded on the Internet Archive (though due to the discontinuation of her serial codes, she can only be used as a trial).

Her voicebank is installed under the name "Carenna Crystal." This name is used for an apparently identical sounding Chinese VOCALOID5 voicebank that remains unreleased, and never officially announced.

(source: vocarchive on archive.org)

[vocalsynthbdays]

happy birthday zhang chuchu(vocaloid 4) !!!!!!! [aug 9]

Zhang Chuchu is a chinese synth developed by Shanghai Wangcheng in collaboration with Migu Comics, and released on 30 apr 2018, though her character birthday is 9 aug. shes voiced by Wan Su, who was chosen through an audition, and her illustrator has not been revealed. chuchu is originally from a manhua called Chǔchǔ Dòng Rén, published by Migu Comics, in which she looked very different. shes a private vb so only select people can use her. she is 21yo and 168cm tall.

chuchu in Chǔchǔ Dòng Rén

logo

ref

[mvvocaloidgifs]

【苍穹·墨清弦·章楚楚原创曲】Hysteria【SinghP】

[welcometothejianghu]

A little Legend of Fei In Real Life tonight, because I feel like looking at pictures of attractive people. (Skipping the two mains, because it's well-documented what they look like out of costume.)

Zhang Hui Wen / Wu Chuchu

Chen Ruo Xuan / Li Sheng

Zhang Xin Yu / Yang Jin

Leng Ji Yuan / Ying Hecong

Sun Jian / Yin Pei

Zhou Jie Qiong / Li Yan

Geng Le / Shen Tianshu

Guo Xin / Mu Xiaoqiao

Dong Xuan / Duan Jiuniang

[missfangirll]

☆°･:*:･｡★ Videos ★ ｡･:*:･°☆

★ 陈情令 | The Untamed ★

☆ Nothing More (Xiao Xingchen) ☆ Memories (Xiao Xingchen/Song Lan) ☆ Der Weg (Xiao Xingchen/Song Lan)   

★ 莲花楼 | Mysterious Lotus Casebook ★

☆ Never your friend (Fang Duobing/Li Lianhua/Di Feisheng) ☆ Coming Home (Fang Duobing/Li Lianhua/Di Feisheng) ☆ Nothing’s Like Home (Fang Duobing/Li Lianhua/Di Feisheng) ☆ Homesick  (Fang Duobing/Li Lianhua/Di Feisheng)

    ★ 盗墓笔记 | The Lost Tomb ★

☆ Read my Lips (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ Saving Grace (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ Never Again (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ Like Real People Do (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ Ugly Heart (The Mystic Nine: Qing Shan Hai Tang, Yan Sanxing) ☆ The Storm (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ Unstoppable (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ Someone you loved (The Lost Tomb: Sand Sea, Wu Xie/Zhang Qiling) ☆ Someone you loved (ver.2) (The Lost Tomb: Sand Sea, Wu Xie/Zhang Qiling) ☆ My Clan (The Lost Tomb & The Mystic Nine: Zhang Family tribute) ☆ The Anthem (The Lost Tomb: Sand Sea, Su Nan) ☆ The Kill (The Mystic Nine: Qing Shan Hai Tang, Yan Sanxing) ☆ Poker Face (The Lost Tomb, Zhang Qiling) ☆ Material Girl (The Lost Tomb: Ultimate Note, Hei Xiazi) ☆ Always been you (The Lost Tomb: Reunion, Kan Jian/Liu Sang) ☆ With Iris (The Lost Tomb: Reunion, Iron Triangle) ☆ A Thousand Years (The Lost Tomb: Reunion, Kan Jian/Liu Sang, Reincarnation AU) ☆ Say Goodbye (The Lost Tomb: Reunion, Wu Xie & Wu Sanxing) ☆ Two (The Lost Tomb: Reunion, Pangzi) ☆ Runaway (The Lost Tomb, Wu Xie/Zhang Qiling) ☆ Stay Alive (The Lost Tomb: Reunion, Wu Xie/Zhang Qiling) ☆ I will not bow (The Lost Tomb: Reunion, Liu Sang) ☆ Counting stars (The Lost Tomb: Sand Sea, Liang Wan/Zhang Rishan) ☆ Seven Wonders (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ Flatline (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ I’ve been blind (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ Rock Bottom (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ Where do lovers go? (The Lost Tomb: Reunion, Wu Xie/Zhang Qiling) ☆ King and Lionheart (The Mystic Nine, Fo Ye & Zhang Rishan) ☆ Time well wasted (The Lost Tomb 2, Wu Xie/Xiao Hua) ☆ The Last Snowfall (Tibetan Sea Flower, Zhang Qiling) ☆ Behind the mask (Tibetan Sea Flower, Zhang Haike & Zhang Haixing) ☆ Warriors (Tibetan Sea Flower, Scorpion Team) ☆ You look good in white (The Lost Tomb Restart: The Grave in the Abyss, Hei Xiazi/Xiao Hua) ☆ All about that bass (DMBJ tiddie tattoo appreciation) ☆ Nice to meet you (The Lost Tomb: Reunion, Wang Pangzi/Ye Piaopiao) ☆ Foolish One (The Lost Tomb: Reunion, Hei Xiazi&/Chuchu) ☆ Accidentally in love (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua) ☆ Pieces (Tibetan Sea Flower, Zhang Qiling/Wu Xie) ☆ 99 Problems (The Lost Tomb: Ultimate Note, Wu Xie) ☆ Glitter and Gold (The Lost Tomb, Zhang Qiling) ☆ Dear Future Husband (The Lost Tomb: Ultimate Note, Hei Xiazi/Xiao Hua)

     ★ 镇魂 | Guardian ★

☆ Favourite Song (Shen Wei/Zhao Yunlan) ☆ Eternity (Shen Wei/Zhao Yunlan) ☆ Shallow (Shen Wei/Zhao Yunlan) ☆ Come to me (Shen Wei/Zhao Yunlan) ☆ I’ll wait (Chu Shuzhi/Guo Changcheng) ☆ Alone (Ye Zun) ☆ Die for you (Shen Wei/Zhao Yunlan) ☆ We won't be falling (Shen Wei/Zhao Yunlan) ☆ Fear of the Water (Shen Wei/Zhao Yunlan) ☆ Silence (Shen Wei/Zhao Yunlan) ☆ We found love (Shen Wei/Zhao Yunlan) ☆ Enough to go by (Shen Wei/Zhao Yunlan) ☆ All the love that I ever needed (Shen Wei/Zhao Yunlan) ☆ These old wheels (Shen Wei/Zhao Yunlan) ☆ Someone to stay (Shen Wei/Zhao Yunlan)

     ★ S.C.I.谜案集 | S.C.I. Mystery ★

☆ True Love (Bai Yutong/Zhan Yao)

               ★ 天官赐福 | Heaven Officials’s Blessing ★

☆ Coming Home (Xie Lian/Hua Cheng)

     ★ 苍兰诀  | Love between Fairy and Devil ★

☆ I used to rule the world (Dongfang Qingcang & Xunfeng)

    ★ KinnPorsche ★

☆ Half a Man (Vegas/Pete) ☆ Poison (Vegas/Pete) ☆ Would you come home (Vegas/Pete)

     ☆ﾟ･:*:･｡★ﾟ You can always send an ask! ★ ｡･:*:･ﾟ☆ ☆

[staincastle]

faz icon da zhang jingyi, por favor!! e queria dizer aqui que sua galeria é a minha fav de todo o tumblr, seus icons sempre são tão maravilhosos que fico até triste de não poder usar todos de uma vez só 😞

olá chuchu!!!! [pani no sistema alguém me desconfigurou] tô aosbdkdn me deixou sem reação de verdade, fiquei >imensamente< feliz por receber essa ask vius, não tenho nem palavras direito pra descrever oq estou sentindo 🫂💗 qjshkd e aqui estão seu icons 📦, muito obrigado por pedir e dar tanto carinho pra galeria, você é incrível 🩷🤲🏻

[confluencextras]

[Image Description: Nine square transparents of different Vocaloids. They are Aoki Lapis, Tone Rion, Anri Rune, Zhang Chuchu, Yuecheng, and Yao Luniang. /end ID]

[celebratedaily]

August 9th - Fictional Birthdays

Yellow Ranger (Mighty Morphin Power Rangers) Soleil (Animal Crossing) Zhang Chuchu (Vocaloid)

[jcmarchi]

Leveraging language to understand machines

New Post has been published on https://thedigitalinsider.com/leveraging-language-to-understand-machines/

Leveraging language to understand machines

Natural language conveys ideas, actions, information, and intent through context and syntax; further, there are volumes of it contained in databases. This makes it an excellent source of data to train machine-learning systems on. Two master’s of engineering students in the 6A MEng Thesis Program at MIT, Irene Terpstra ’23 and Rujul Gandhi ’22, are working with mentors in the MIT-IBM Watson AI Lab to use this power of natural language to build AI systems.

As computing is becoming more advanced, researchers are looking to improve the hardware that they run on; this means innovating to create new computer chips. And, since there is literature already available on modifications that can be made to achieve certain parameters and performance, Terpstra and her mentors and advisors Anantha Chandrakasan, MIT School of Engineering dean and the Vannevar Bush Professor of Electrical Engineering and Computer Science, and IBM’s researcher Xin Zhang, are developing an AI algorithm that assists in chip design.

“I’m creating a workflow to systematically analyze how these language models can help the circuit design process. What reasoning powers do they have, and how can it be integrated into the chip design process?” says Terpstra. “And then on the other side, if that proves to be useful enough, [we’ll] see if they can automatically design the chips themselves, attaching it to a reinforcement learning algorithm.”

To do this, Terpstra’s team is creating an AI system that can iterate on different designs. It means experimenting with various pre-trained large language models (like ChatGPT, Llama 2, and Bard), using an open-source circuit simulator language called NGspice, which has the parameters of the chip in code form, and a reinforcement learning algorithm. With text prompts, researchers will be able to query how the physical chip should be modified to achieve a certain goal in the language model and produced guidance for adjustments. This is then transferred into a reinforcement learning algorithm that updates the circuit design and outputs new physical parameters of the chip.

“The final goal would be to combine the reasoning powers and the knowledge base that is baked into these large language models and combine that with the optimization power of the reinforcement learning algorithms and have that design the chip itself,” says Terpstra.

Rujul Gandhi works with the raw language itself. As an undergraduate at MIT, Gandhi explored linguistics and computer sciences, putting them together in her MEng work. “I’ve been interested in communication, both between just humans and between humans and computers,” Gandhi says.

Robots or other interactive AI systems are one area where communication needs to be understood by both humans and machines. Researchers often write instructions for robots using formal logic. This helps ensure that commands are being followed safely and as intended, but formal logic can be difficult for users to understand, while natural language comes easily. To ensure this smooth communication, Gandhi and her advisors Yang Zhang of IBM and MIT assistant professor Chuchu Fan are building a parser that converts natural language instructions into a machine-friendly form. Leveraging the linguistic structure encoded by the pre-trained encoder-decoder model T5, and a dataset of annotated, basic English commands for performing certain tasks, Gandhi’s system identifies the smallest logical units, or atomic propositions, which are present in a given instruction.

“Once you’ve given your instruction, the model identifies all the smaller sub-tasks you want it to carry out,” Gandhi says. “Then, using a large language model, each sub-task can be compared against the available actions and objects in the robot’s world, and if any sub-task can’t be carried out because a certain object is not recognized, or an action is not possible, the system can stop right there to ask the user for help.”

This approach of breaking instructions into sub-tasks also allows her system to understand logical dependencies expressed in English, like, “do task X until event Y happens.” Gandhi uses a dataset of step-by-step instructions across robot task domains like navigation and manipulation, with a focus on household tasks. Using data that are written just the way humans would talk to each other has many advantages, she says, because it means a user can be more flexible about how they phrase their instructions.

Another of Gandhi’s projects involves developing speech models. In the context of speech recognition, some languages are considered “low resource” since they might not have a lot of transcribed speech available, or might not have a written form at all. “One of the reasons I applied to this internship at the MIT-IBM Watson AI Lab was an interest in language processing for low-resource languages,” she says. “A lot of language models today are very data-driven, and when it’s not that easy to acquire all of that data, that’s when you need to use the limited data efficiently.” 

Speech is just a stream of sound waves, but humans having a conversation can easily figure out where words and thoughts start and end. In speech processing, both humans and language models use their existing vocabulary to recognize word boundaries and understand the meaning. In low- or no-resource languages, a written vocabulary might not exist at all, so researchers can’t provide one to the model. Instead, the model can make note of what sound sequences occur together more frequently than others, and infer that those might be individual words or concepts. In Gandhi’s research group, these inferred words are then collected into a pseudo-vocabulary that serves as a labeling method for the low-resource language, creating labeled data for further applications.

The applications for language technology are “pretty much everywhere,” Gandhi says. “You could imagine people being able to interact with software and devices in their native language, their native dialect. You could imagine improving all the voice assistants that we use. You could imagine it being used for translation or interpretation.”

[burgertronfangirl]

Which Vocaloid cardiophilia character will I roleplay? part 1

Zhanyin Lorra

Zhang Chuchu

Yuzuki Yukari

Yumemi Nemu

Yuezheng Ling

Yanhe

Xingchen

Xin Hua

Vy1

Uni

Tone Rion

Tohoku Zunko

Sweet Ann

Sonika

Sf-A2 Miki

Seeu

Sarah

Sachiko

Ruby

Ring Suzune

Rana

Prima

Otori Kohaku

Otomachi Una

Ona

Nekomura Iroha

Mo Qingxian

Miriam

Mirai Komachi

Mew

Merli

Meiko

Meika Mikoto

Meika Hime

Megurine Luka

Mayu

Masaoka Azuki

Maika

Macne Petit

Macne Nana

[vocaloidfactoftheday]

All About Private Vocaloids!

a while ago i made a post about canceled vocaloids. this is a sort of sequel post about some private vocaloids. often these vocaloids are made and given only to exclusive users, eventually expiring or being retired. when it comes to abandoned vocaloids, private vocaloids and vocaloids that were never completed/released tend to be grouped together.

all information and images are from the vocaloid wiki unless stated otherwise.

the vocaloids discussed in this post are:

Kobayashi Matcha and Masaoka Azuki

Akikoloid-chan

Ueki-loid

Anri Rune

hide

Zhang Chuchu and Yuecheng

Kobayashi Matcha and Masaoka Azuki

Engine: VOCALOID2

Language: Japanese

Company: SEGA in collaboration with YAMAHA

Status: Retired; replaced with public VOCALOID4 voicebanks

They were made for use in Project 575, a multimedia franchise including several games and a series of 5 short anime episodes.

Specifically, the games Utayomi 575 and Uta Kumi 575 used the VOCALOID2 engine to synthesize their vocals in real time.

Their private use made them notable targets of piracy. Their voicebanks were cracked by extracting the voicebank data from Utayomi 575 and making them usable for VOCALOID2.

In 2017, they received VOCALOID4 updates and are now commercially available under the names MATCHA and AZUKI. These are the first private vocals to be made public, although their original VOCALOID2 voicebanks are still legally unobtainable.

Akikoloid-chan

Engine: VOCALOID3

Language: Japanese

Company: Lawson, Inc.

Status: Retired

Akikoloid-chan is a VOCALOID derivative of Akiko-chan, the new mascot for Lawson in 2011.

Lawson was the only group with the license to use her. She was used as a mascot on the Lawson Nico Nico Douga channel to help promote Lawson.

Akikoloid-chan is no longer used for music. However, Lawson still owns her character.

The mascot she originated from, Akiko-chan, is now a VTuber on the Lawson YouTube channel.

Ueki-loid

Engine: VOCALOID3

Language: Japanese

Company: Music Airport Inc.

Status: Unknown; possibly abandoned

This is the first use of VOCALOID that is an attempt to "revive" a deceased singer by emulating their vocals. The singer in question is Hitoshi Ueki, who passed away in 2007.

The voicebank was made by first recording the vocals of Hitoshi Ueki's oldest son, Hiro Kouichi. Then, they studied the differences between his and his father's voice, and edited the recordings to match Hitoshi Ueki's tone.

Only a few demos have been made for Ueki-loid. An album of songs was planned, but has never been released and has received no news since 2012.

It's possible that Ueki-loid was simply a test for the technology of reviving deceased singers' voices.

Anri Rune

Engine: VOCALOID3

Language: Japanese

Company: Fuji TV

Status: Retired

Anri Rune was originally a newscaster character on Fuji TV. Her career as a newscaster was short-lived, as she failed to bring in enough ratings to satisfy the network, and so she was retired.

In 2013, Anri Rune was repurposed as a VOCALOID mascot. She was given a new appearance and biographical information. She was also given a demo song by producer Kikuo, titled Hallelujah Super Idol.

After her single demo, there was no news on Rune's status. In response to a fan, Kikuo did not know her current status. YAMAHA also stated that Rune was never intended as a commercial product.

In May 2015, about 2 years after her debut, Fuji TV confirmed that Rune was retired and no products with her were planned.

"hide"

Engine: VOCALOID3

Language: Japanese

Company: Headwax Organization Co., Ltd.

Status: Unknown

Another attempt to "revive" a deceased singer, this time basing the vocal off of Matsumoto Hideto, better known as hide, the lead guitarist of rock band X-Japan who passed away in 1998.

Unlike Ueki-loid, samples were taken directly from recordings of hide's voice, not from any relatives.

The voicebank was used in the album Co Gal, which began production in 1998. hide was unable to complete the album before his death; the VOCALOID voicebank was used to complete the album with his voice.

The album was then released in December 2014. Fans remarked that the voice was unmistakably reminiscent of hide.

Due to using hide's voice, he is credited as the singer of all the songs in the Co Gal album despite the use of VOCALOID. Because of this, the actual name of the software itself is unknown, and is usually simply also referred to as "hide."

The status of this voicebank is unknown; it has not had any known usage since Co Gal.

Zhang Chuchu and Yuecheng (King)

(sorry chuchu for the crop)

Engine: VOCALOID4

Language: Chinese

Company: Shanghai Wangcheng

Status: Possibly abandoned

Chuchu and Yuecheng both originally appeared as characters in manhua. Chuchu was owned by Migu Comics while Yuecheng was owned by NetEase comics.

Shanghai Wangcheng, who had also worked with Gynoid on Xin Hua, wanted to create business-to-business VOCALOID voicebanks for private use, to turn preexisting characters into virtual idols, and approached these companies with the offer to develop VOCALOID4 voicebanks for their characters.

Both VOCALOIDs' voice providers were contest winners. The voicebanks were complete by April 30, 2018 and continued to be used by their authorized users.

In June 2020, an authorized user of these voicebanks reported that their serial codes had ceased distribution. YAMAHA had ended contracts with Shanghai Wangcheng, and Shanghai Wangcheng has since ceased activity.

This is a similar situation to the discontinuation of Utatane Piko. This does not stop authorized users from using these voicebanks, but no new users can gain access, and if switching computers, they can only be used for a 2 week trial period.

i hope you found this interesting! thanks!

[varian-polis]

Geez Polis how many of these did you finish but not post

This is the last one for now, I swear