27 September – 1 October, ICC, Sydney, Australia
'Speaking Together'
Proudly hosted by the Australasian Speech Science and Technology Association (ASSTA) and the International Speech Communication Association (ISCA).
🕒 Submissions close today – 3 November 2025
👉 interspeech2026.org/en-AU/pages/...
🕒 Submissions close today – 3 November 2025
👉 interspeech2026.org/en-AU/pages/...
🕒 Submissions close today – 3 November 2025
👉 interspeech2026.org/en-AU/pages/...
🕒 Submissions close today – 3 November 2025
👉 interspeech2026.org/en-AU/pages/...
Shape the conversations that will define speech research in 2026.
🗓 Deadline: 3 Nov 2025
🌏 Sydney, 27 Sept – 1 Oct 2026
🔗 interspeech2026.org/en-AU/pages/...
Shape the conversations that will define speech research in 2026.
🗓 Deadline: 3 Nov 2025
🌏 Sydney, 27 Sept – 1 Oct 2026
🔗 interspeech2026.org/en-AU/pages/...
Help drive innovation in the speech sciences.
🗓️ Closes 3 November 2025
🔗 interspeech2026.org/en-AU/pages/calls/call-for-special-sessions-and-challenges
Help drive innovation in the speech sciences.
🗓️ Closes 3 November 2025
🔗 interspeech2026.org/en-AU/pages/calls/call-for-special-sessions-and-challenges
🗓 Closes 3 Nov 2025
🔗 interspeech2026.org/en-AU/pages/...
🗓 Closes 3 Nov 2025
🔗 interspeech2026.org/en-AU/pages/...
🗓️ Deadline: 3 November 2025
🔗 interspeech2026.org/en-AU/pages/calls/call-for-special-sessions-and-challenges
🌏 Sydney | *Speaking Together*
🗓️ Deadline: 3 November 2025
🔗 interspeech2026.org/en-AU/pages/calls/call-for-special-sessions-and-challenges
🌏 Sydney | *Speaking Together*
📆 Sydney – 27 September – 1 October 2026
📆 Sydney – 27 September – 1 October 2026
#Interspeech2025 kicks off next week in Rotterdam, the Netherlands 🗣️🌍
We can’t wait to welcome everyone for a week full of talks, posters, workshops & networking.
📅 See you soon!
Comment below, are you joining? 🥰
#Interspeech2025 kicks off next week in Rotterdam, the Netherlands 🗣️🌍
We can’t wait to welcome everyone for a week full of talks, posters, workshops & networking.
📅 See you soon!
Comment below, are you joining? 🥰
🤖 Hackathon: Ben jij tussen de 10 en 18 jaar en geïnteresseerd in robots en programmeren? Doe dan mee aan onze hackathon! In teams van drie werk je samen om onze robots te helpen bij een spannende missie uit de ruimte.
🤖 Hackathon: Ben jij tussen de 10 en 18 jaar en geïnteresseerd in robots en programmeren? Doe dan mee aan onze hackathon! In teams van drie werk je samen om onze robots te helpen bij een spannende missie uit de ruimte.
Ontdek hoe we communiceren, hoe tech onze stemmen begrijpt – en veel meer!
📍Ahoy, Rotterdam
🕙 17/8, 10-17u
Ontdek hoe we communiceren, hoe tech onze stemmen begrijpt – en veel meer!
📍Ahoy, Rotterdam
🕙 17/8, 10-17u
Op 17/8 ben je van harte welkom op het Speech Science Festival in Ahoy Rotterdam!
----
EN: Are you curious about language, technology, and science?
Join us on Aug 17 at the Speech Science Festival in Ahoy Rotterdam!
Op 17/8 ben je van harte welkom op het Speech Science Festival in Ahoy Rotterdam!
----
EN: Are you curious about language, technology, and science?
Join us on Aug 17 at the Speech Science Festival in Ahoy Rotterdam!
🔹 Platinum: Meta
💎 Diamond: Apple, Google
🥈 Silver: LXT, DataForce by TransPerfect
🥉 Bronze: Appen
✨ 10K Impact: Amazon Science
See you in Rotterdam this August!
🔗 interspeech2025.org
🔹 Platinum: Meta
💎 Diamond: Apple, Google
🥈 Silver: LXT, DataForce by TransPerfect
🥉 Bronze: Appen
✨ 10K Impact: Amazon Science
See you in Rotterdam this August!
🔗 interspeech2025.org
"Creating sound with Praat" by Paul Boersma – yes, the creator of Praat!
✅ Formulas, glottal pulses, spectra
✅ Articulatory & acoustic synthesis
✅ LLM-powered TTS
✅ Perfect for phonetics & speech tech
🔗 interspeech2025.org
"Creating sound with Praat" by Paul Boersma – yes, the creator of Praat!
✅ Formulas, glottal pulses, spectra
✅ Articulatory & acoustic synthesis
✅ LLM-powered TTS
✅ Perfect for phonetics & speech tech
🔗 interspeech2025.org
Join this #Interspeech2025 tutorial on Long-Context ASR
📍 Rotterdam
✅ Multi-speaker ASR
✅ RAG-based error correction
✅ LLM integration
✅ Fair & inclusive systems
🔗 interspeech2025.org
Join this #Interspeech2025 tutorial on Long-Context ASR
📍 Rotterdam
✅ Multi-speaker ASR
✅ RAG-based error correction
✅ LLM integration
✅ Fair & inclusive systems
🔗 interspeech2025.org
Automatic Quality Assessment for Speech and Beyond
✅ From DNN-based SQA to audio-wide evaluation
🛠️ Includes hands-on with SHEET & VERSA toolkits
📍 Rotterdam | Don’t miss it!
🔗 interspeech2025.org
Automatic Quality Assessment for Speech and Beyond
✅ From DNN-based SQA to audio-wide evaluation
🛠️ Includes hands-on with SHEET & VERSA toolkits
📍 Rotterdam | Don’t miss it!
🔗 interspeech2025.org
🔍 "Interpretability Techniques for Speech Models"
🧠 Learn to peek inside black-box speech models
⚙️ Hands-on with probing, analysis & feature extraction
📅 Join us in Rotterdam!
🔗 interpretingdl.github.io/speech-inter...
🔍 "Interpretability Techniques for Speech Models"
🧠 Learn to peek inside black-box speech models
⚙️ Hands-on with probing, analysis & feature extraction
📅 Join us in Rotterdam!
🔗 interpretingdl.github.io/speech-inter...
"Speech Watermarking" w/ Patrick O'Reilly & Bryan Pardo
✅ Add invisible ID to synthetic speech
✅ Learn signal-based & neural watermarking
✅ Test robustness vs. attacks
✅ Protect voice integrity
🔗 interspeech2025.org
"Speech Watermarking" w/ Patrick O'Reilly & Bryan Pardo
✅ Add invisible ID to synthetic speech
✅ Learn signal-based & neural watermarking
✅ Test robustness vs. attacks
✅ Protect voice integrity
🔗 interspeech2025.org
A Journey through Emerging Speech Research with NVIDIA NeMo
✨Topics:
FastConformer + CUDA Graphs
Diffusion models for speech enhancement
Neural audio codecs
Canary-1B, Sortformer, SALM & BESTOW
Training tricks: 2x speedup
👉interspeech2025.org
A Journey through Emerging Speech Research with NVIDIA NeMo
✨Topics:
FastConformer + CUDA Graphs
Diffusion models for speech enhancement
Neural audio codecs
Canary-1B, Sortformer, SALM & BESTOW
Training tricks: 2x speedup
👉interspeech2025.org
Interpretable Stats for Speech Science
📈 Learn:
Causal & Bayesian modeling
Mixed-effects & GAMs
Real examples, no heavy math
📍For speech researchers & clinicians
🌐 interspeech2025.org
Interpretable Stats for Speech Science
📈 Learn:
Causal & Bayesian modeling
Mixed-effects & GAMs
Real examples, no heavy math
📍For speech researchers & clinicians
🌐 interspeech2025.org