kodhandarama(shreeram)

PhD in speech synthesis, carnatic rasika, on a quest to visit all national parks

[Yassine Taoudi-Benchekroun @TBen_Yassine]

The greatest diagnosis of Academia's problem I've ever heard, from @kyosu (Jakob Uszkoreit, from transformers original paper)

"One should fall in love with the problem, not with the solution"

Once you notice this, you see it *everywhere* in academia

[kodhandarama(shreeram) @cricketrasika]

@Nithya_Shrii

[Berrak Sisman @berraksismann]

Our lab has 4 papers accepted at AACL 2026! @aaclmeeting. We focus on emotional voice conversion with LALMs, audio reasoning in LALMs, a new benchmark on speaking style captioning in LALMs, and Alzheimer's detection. Students will be in China presenting these papers. 😊@jhuclsp

[Berrak Sisman @berraksismann]

Excited to share our work, Brain2Speech-Net!🧠🗣️ We synthesize intelligible speech directly from intracortical neural activity (recorded from brain using implanted microelectrode arrays), while a patient with ALS attempts to speak.
@cricketrasika @jhuclsp https://t.co/1g8XvVSp0Z

[vik @vikhyatk]

humans are just stochastic parrots. true intelligence requires the transformer architecture

[Berrak Sisman @berraksismann]

My lab at @jhuclsp is looking for Master's students! 😊If you're a JHU student interested in pursuing research with me, email me your CV. We work on speech and language technologies, including generation, security, healthcare, and more.
https://t.co/FhSNZ0uXOI @JohnsHopkins

[kodhandarama(shreeram) @cricketrasika]

@sah_ficus

[kodhandarama(shreeram) @cricketrasika]

A tweet I had promised my old self :')

[kodhandarama(shreeram) @cricketrasika]

@derangineer Thanks Deb!☺️

[Veeraraju Elluru @VeerarajuE]

anybody see any update to their ARR reviews? the July 17 AoE deadline has long passed and i see absolutely no response/ack of the rebuttals smh

[kodhandarama(shreeram) @cricketrasika]

Knowing when to start a new Claude chat mid-task is a separate skill in itself

[Audio and Speech Processing Papers @AudioAndSpeech]

TRACE-EVC: Text-Guided Relative Affective Control for Zero-Shot Emotional Voice Conversion

Zihan Zhang, Shreeram Suresh Chandra, Zongyang Du, Xiutian Zhao, Aurosweta Mahapatra, Hao Zhang, Philipp Koehn, Berrak Sisman
https://t.co/DvBDrEmH8L [𝚎𝚎𝚜𝚜.𝙰𝚂 𝚎𝚎𝚜𝚜.𝚂𝙿]

[François Chollet @fchollet]

While the writing style of LLMs is still as recognizable as ever, a new trend is that humans have started organically writing like them, too (which makes sense: of course you would end up imitating the style you are constantly reading). That makes telling the difference between humans and clankers a bit more challenging.

[kodhandarama(shreeram) @cricketrasika]

Lesgoo Ahad!

[ahad @ahadj0]

what if we treated robot actions like audio waveforms?

introducing neural action codec (NAC)

a method for creating a compressed action vocabulary to train VLA policies

[Berrak Sisman @berraksismann]

Recruiting PhD students for Fall 2027 at @JohnsHopkins @jhuclsp! My lab works on speech and language, from generation to security and healthcare applications. If you're interested, please apply to the JHU ECE PhD program (select me as a potential advisor). https://t.co/3XQvTaUINn

[Royal Challengers Bengaluru @RCBTweets]

🏆🏆🏆🏆
🏆
🏆
🏆🏆🏆🏆
🏆
🏆
🏆🏆🏆🏆

[Ramin Nasibov @RaminNasibov]

My first AI assistants

[kodhandarama(shreeram) @cricketrasika]

All fish in a pond. How big of a fish do you think you are? How big of a pond do you think you're in? What do fish sizes around you tell you? There's always smaller fish and bigger ponds and bigger fish and smaller ponds.

[Paras Chopra @paraschopra]

We made LLMs speak Tulu, a language with only 2 million speakers.

It wasn't easy because LLMs kept confusing it with Kannada, but we discovered negative constraints really help.

[ً @manmarziiyaan]

Who is Jasprit Bumrah? To the blind, he is the light. To the hungry, he is bread. To the sick, he is the cure. To the lonely, he is company. To the sad, he is joy. To the prisoner, he is freedom. For the poor, he is a treasure. For me, he is everything.