Top Tweets for #speechprocessing
Deepfake detection achieves 0.95% error on mixed audio with prompt-tuned SSL models. Deploy on noisy real-world speech. MixFake benchmark released. #AudioDeepfakes #AudioForensics #SpeechProcessing https://t.co/JjOr4Fb2SB
๐จ New Paper Alert!
speech-emotion: a multilingual & multimodal toolkit for emotion recognition ๐๏ธ๐ฌ
โ
Combines audio + text โ better performance than unimodal models
โ
Supports Spanish ๐ช๐ธ & English ๐ฌ๐ง
SoftwareX (Elsevier)
https://t.co/SH2q6R11Jx
#NLPoc #SpeechProcessing
๐๏ธ Smarter conversations with Voice AI
Transcribe, understand & respond in real-time ๐
Boost support & automate interactions effortlessly
๐ https://t.co/5Jal9N0gG9
#speechprocessing #artificialintelligence #voiceaisolutions #speechrecognitionconversationalai #levelsai
๐ PhD Thesis Defended (Apr 27, 2026)
Green & Inclusive Speech Processing (bias, sustainability, Indian languages)
๐ ACLโ25 (Outstanding Paper), NAACLโ24/โ22, LRECโ26
๐ Grateful to @DrAnubhaGupta
๐ฌ Open to academic opportunities
#SpeechProcessing #ResponsibleAI #IIITD
๐๏ธ Voice ai & speech processing ๐ค
Turn conversations into insights and experiences into intelligent interactions โก
๐https://t.co/5Jal9N0gG9
#voiceai #speechprocessing #artificialintelligence #aitechnology #machinelearning #digitaltransformation #voiceassistant #levelsai
University of Sheffield invites applications for MSc speech, NLP, September 2026
Report: https://t.co/NlgA4MtPRF
#UniversityOfSheffield #MScNLP #AI #MachineLearning #SpeechProcessing #NaturalLanguageProcessing
atkAudio atkAutoEq: Dynamic EQ for Speech & Post-Production
.
#ATKAUDIO #ATKAUTOEQ #AU #AUDIOPLUGIN #AUTOMATICEQUALIZER #DEESSER #DIALOGUEEDITING #DYNAMICEQ #LINUX #LIVESOUND #MACOS #POSTPRODUCTION #SPECTRALDYNAMICS #SPEECHPROCESSING #VST3 #WINDOWS
๐
DeepMind is hiring Research Scientist
๐ Tokyo, Japan
๐ช #AI #Machine Learning #python #deeplearning #naturallanguageprocessing #computervision #speechprocessing
#tech #softwareengineer #jobs
https://t.co/YXwc4SpEMs
๐ย Happy to share that "SpeechMapper: Speech-to-text Embedding Projector for LLMs" has been accepted toย #ICASSP2026!
This work was done during my internship at NAVER LABS Europe with Marcely Zanon Boito and Ioan Calapodescu.
#MultimodalAI #SpeechLM #SpeechProcessing
Thread 1/4
Domain adversarial training for robust pathological voice classification across microphones #DomainAdversarialTraining #PathologicalVoice #SpeechProcessing
International Robotics and Automation Awards
Visit Us: https://t.co/tsUXfhL8k8
Nomination:https://t.co/SHfgLi28AO
Three papers from our unit have been accepted to ICASSP 2026! See you in Barcelona for discussions! #ICASSP2026 #ICASSP #SignalProcessing #AI #SpeechProcessing
Happy to share some exciting news!
"MAGE: A Coarse-to-Fine Speech Enhancer with Masked Generative Model" has been accepted to ICASSP 2026 ๐ IEEE conference on Acoustics, Speech, and Signal Processing.
#ICASSP2026 #SpeechProcessing #SpeechEnhancement
https://t.co/XJY0oLphHk
Iโm currently working on a research project focused on non-intrusive stress detection using multimodal deep learning (audio + video + transformers). Early results are promisingโmore details coming soon.
#AI #ML #ComputerVision #SpeechProcessing
We are pleased to announce the release of SPTK 4.4!๐
In this update, the raw2wav and wav2raw commands are back. We are also planning to add a resampling command in the near future.
https://t.co/D3VglhhJVe
#SpeechProcessing
My first paper, โAttention Enhanced Speaker Representation with Contrastive Learning,โ is now published at an IEEE Conference
https://t.co/fRNEpPHtfu
#FirstPublication #IEEE #MachineLearning #SpeechProcessing #ResearchJourney
Meet the @ijaonline Associate Editors, Samira Anderson is a Professor in Audiology at the @UofMaryland. Her research interests include the neural mechanisms underlying #speechprocessing deficits in older adults and approaches to induce #neuroplasticity to reverse these deficits.
Nvidia Unveils Advanced AI Models for Autonomous Driving and Speech Processing at NeurIPS
https://t.co/gp5dqZHKDJ
#aiinfrastructuregpus #ainews #multimodalai
#aimodels #autonomousdriving #gputechnology #neurips #nvidia #speechprocessing
3/3 Balancing reduces false negatives, vital for screening. Congrats to @XavierSanc2433, PhD student and first author, for his hard work.
#MentalHealth #SpeechProcessing #EMD #IMF #MachineLearning
We canโt fix what we donโt measure.
Thatโs why I build evaluation frameworks for speech & conversational AI โ so we can stress-test systems against real-world variability.
#AIResearch #Evaluation #SpeechProcessing
sherpa-onnx offers advanced speech processing: ASR, TTS, VAD, and more. Supports multiple platforms & languages. Great for audio apps! https://t.co/gru9rpsq79 #SpeechProcessing #OpenSource
Last Seen Hashtags on Sotwe
hijab
Seen from Indonesia
เธเธฑเธเนเธขเนเธเนเธซเธฅเธกเธเธเธฑเธ
Seen from Thailand
toton
Seen from Austria
๋ฐฉ๊ท๋
ธ์
Seen from Korea
Hinata
Seen from Germany
Tasteofchoklit
Seen from United Kingdom
เธเธงเธเธญเธดเธชเธฃเธฐ
Seen from Thailand
yesbys
Seen from United States
desfiledominicanodenj
เธเธฒเธเธเธดเนเธ
Seen from Thailand
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
240.1M followers
Barack Obama
@barackobama
119.3M followers
Donald J. Trump
@realdonaldtrump
111.6M followers
Cristiano Ronaldo
@cristiano
108.8M followers
Narendra Modi
@narendramodi
106.9M followers
Rihanna
@rihanna
97.2M followers
NASA
@nasa
92.1M followers
Justin Bieber
@justinbieber
90.5M followers
KATY PERRY
@katyperry
86.7M followers
Taylor Swift
@taylorswift13
80.5M followers
Lady Gaga
@ladygaga
72.1M followers
Kim Kardashian
@kimkardashian
69.3M followers
YouTube
@youtube
68.6M followers
Virat Kohli
@imvkohli
68.4M followers
Bill Gates
@billgates
63.4M followers
The Ellen Show
@theellenshow
62.5M followers
CNN
@cnn
61.9M followers
Neymar Jr
@neymarjr
60.9M followers
X
@x
60.9M followers
CNN Breaking News
@cnnbrk
59.9M followers