Neil Zeghidour

10 statements across 1 episodes · 2 bullish · 5 bearish · 1 people on the record · first statement Feb 19, 2026 by Neil Zeghidour · across every show →

On the record as a speaker too: Neil Zeghidour's record, appearances and statements → this page counts the times other people say the name.

Everything said about Neil Zeghidour, oldest first

Feb 19, 2026 negative
Opinion
Zeghidour: Generating video and audio separately ignores inherent multimodal training data
“I don't think it really makes sense to do video to audio generation separately, because typically the data exists as a multimodal signal, right?”
Neil Zeghidour Feb 19, 2026 ▶ 1:13:29 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 negative
Insight
Zeghidour: Training AI to learn world knowledge from speech is terrible
“Getting your model to learn about the world from speech, I think it's a terrible idea.”
Neil Zeghidour Feb 19, 2026 ▶ 57:17 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026
Insight
Zeghidour: Cascaded voice AI loses paralinguistic info in text bottleneck
“By going through the bottleneck of text, you lose what we call paralinguistic information, which is all the information we convey when we speak on top of what we say.”
Neil Zeghidour Feb 19, 2026 ▶ 48:08 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026
Insight
Zeghidour: Selective compute usage is essential for voice AI economics
“So being very selective about when to compute, to use compute, I think that's the only way to, for all of it to make sense economically.”
Neil Zeghidour Feb 19, 2026 ▶ 1:04:03 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 positive
Assertion Contradicted
Zeghidour: Kyutai's Moshi remains the only full-duplex conversational AI model
“Moshi, that is still to the day the only full duplex model.”
Neil Zeghidour Feb 19, 2026 ▶ 25:45 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 positive
Prediction Not checkable as stated
Zeghidour: AI voice design will eliminate the need for voice cloning
“Voice design is going to, you know, just remove this issue because then again, people typically are going to clone the voice of someone, but what they wanted is someone from a specific gender, specific demographics, age, accent, and so on. And so they could ju…”
Neil Zeghidour Feb 19, 2026 ▶ 1:12:08 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 negative
Opinion
Zeghidour: Audio watermarking is a scam and easily broken
“Watermarking is a scam. I'm sorry, I have to say it. It just doesn't work. I worked on it. We have an appendix in the Moshi paper around how we could break so easily any watermarking that was supposed to be state of the art. So people should not rely on that.”
Neil Zeghidour Feb 19, 2026 ▶ 1:09:16 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 bearish
Assertion Not checkable as stated
Zeghidour: Zero progress made on noisy multi-speaker understanding in 10 years
“In TTS, we see a lot of progress. For this kind of hard understanding problem, I hear people saying the exact same stuff as they did 10 years ago. Like, there was zero progress.”
Neil Zeghidour Feb 19, 2026 ▶ 56:03 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026
Assertion Not checkable as stated
Zeghidour: Only 50 people worldwide can train competitive voice AI models
“Between 10 and 100? No, I would say. 50? I don't know. It's hard to say. But, yeah, I think it's very few and, really meaningful contributions that have pushed the field forward have been made by very small groups of people.”
Neil Zeghidour Feb 19, 2026 ▶ 6:55 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Feb 19, 2026 bearish
Prediction Not checkable as stated
Zeghidour: No AI team will solve noisy multi-speaker recognition within a year
“Well, I would say a frontier is I could like bet to every single speech team in the world that they don't solve it in the next year or so. It's a robot in the model in the factory, and there is a lot of noise from machines, and you have a lot of people talking…”
Neil Zeghidour Feb 19, 2026 ▶ 53:34 Voice AI’s Big Moment: Top Researcher on Why Everything Is Changing (Neil Zeghidour, Gradium AI)
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.