If you're in Rotterdam for Interspeech, join us on Monday for the special session on Interpretability in Speech Technology

🕚 August 18th, 11:00 AM

📍Dock 15

🎙️ 𝐊𝐞𝐲𝐧𝐨𝐭𝐞 by 𝑃𝑟𝑜𝑓. 𝐾𝑎𝑟𝑒𝑛 𝐿𝑖𝑣𝑒𝑠𝑐𝑢

🖼️ 𝐏𝐨𝐬𝐭𝐞𝐫 𝐬𝐞𝐬𝐬𝐢𝐨𝐧 for 15 accepted papers

#Interspeech2025

📢 #SpeechTech & #SpeechScience researchers!
We are thrilled to announce that Prof. Karen Livescu will keynote our Special Session on Interpretable Audio and Speech Models at #Interspeech2025:
"What can interpretability do for us (and what can it not)?"
🗓️ Aug 18, 11:00
@interspeech.bsky.social

We also release our robust model and multi-domain evaluation benchmark to the research community

Model huggingface.co/badrex/mms-3...

Eval Dataset 🛢️

New paper in Interspeech 2025 🚨
@interspeech.bsky.social

A Robust Model for Arabic Dialect Identification using Voice Conversion

Paper 📝 arxiv.org/pdf/2505.24713
Demo 🎙️https://shorturl.at/rrMm6

#Arabic #SpeechTech #NLProc #AI #Speech #ArabicDialects #Interspeech2025 #ArabicNLP

Today is #Interspeech2025 deadline

Don't forgot to submit your work to the special session on Interpretability in Audio & Speech Technology, if it fits the theme

We are looking forward to see exciting submissions ✨

#SpeechTech #SpeechScience

Humans vs Ants: Problem-solving Skills

Phase Transition xkcd.com/3025

I wanted to show that you could ask these questions about pretty much any language (including English). But I'm glad you asked these questions because this opinion is very common among NLP practitioners and I'm curious how we should respond

Shoutout to fellow organizers: Aravind Krishnan @a-krishnan.bsky.social, Francesco Paissan @fpaissan.bsky.social, Cem Subakan, Mirco Ravanelli, and Dietrich Klakow

📣 #SpeechTech & #SpeechScience people

We are organizing a special session at #Interspeech2025 on: Interpretability in Audio & Speech Technology

Check out the special session website: sites.google.com/view/intersp...

Paper submission deadline 📆 12 February 2025

In a different universe:

Why do we publish English only resources?
linguistic findings?❌ weak due to focus on a single language
support model multilinguality? ❌so why this specific morphologically poor language?
Spoken by a large population?❌ why don't work on Mandarin instead?

That's rigth. It is just an NN, only one hidden layer

Another question to the speech community here: Which paper is considered to be the first paper on speech recognition that used DNNs?
This one: Acoustic Modeling using Deep Belief Networks
Abdel-rahman Mohamed, George E. Dahl, and Geoffrey Hinton? IEEE TASLP

or another...?

It depends on what you mean by speech recognition

If you have a broad definition, you could back to 1980s 😁

pubs.aip.org/asa/jasa/art...

I am working on speech translation nowadays, does that count as MT? 😁

Damn Duo!

I did not need a reminder of that 😅

#Duolingo

Nah I don't like question answering. For answers please see Yoav Goldberg's comment

Not this bit.

But "So far it seems they [LLMs] have been a great toy." is indeed a controversial opinion

Yoav Goldberg answered Zerak's question in his comment (from an NLP practioner's perspective), although LLMs are not just for NLP stuff

Do you seriously mean that or you intentionally wrote a controversial opinion so people come and attack you? 😁

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP - work led by @mariusmosbach.bsky.social, and done in collaboration with Tomás Vergara-Browne and Mor Geva
aclanthology.org/2024.emnlp-m...

I've started putting together a starter pack with people working on Speech Technology and Speech Science: go.bsky.app/BQ7mbkA

(Self-)nominations welcome!

Hello there 👋🏼