#speechprocessing - Twitter Hashtag

about 1 month ago

Built a phoneme-level pronunciation scorer 🎙️ Audio + target sentence → per-phoneme scores and a coaching tip for the worst sound. No fine-tuning, no LLM. Runs 3.9x real-time on one CPU core. Demo 👇 #NLProc #SpeechProcessing #MachineLearning

1

5

0

2

182

NLP_UMUTeam @NLP_umuteam

6 months ago

🚨 New Paper Alert! speech-emotion: a multilingual & multimodal toolkit for emotion recognition 🎙️💬 ✅ Combines audio + text → better performance than unimodal models ✅ Supports Spanish 🇪🇸 & English 🇬🇧 SoftwareX (Elsevier) https://t.co/SH2q6R11Jx #NLPoc #SpeechProcessing

0

5

6

1

215

Divya Sharma @vdivyasharma

6 months ago

🎓 PhD Thesis Defended (Apr 27, 2026) Green & Inclusive Speech Processing (bias, sustainability, Indian languages) 🏆 ACL’25 (Outstanding Paper), NAACL’24/’22, LREC’26 🙏 Grateful to @DrAnubhaGupta 🔬 Open to academic opportunities #SpeechProcessing #ResponsibleAI #IIITD

vdivyasharma's tweet photo. 🎓 PhD Thesis Defended (Apr 27, 2026)

Green & Inclusive Speech Processing (bias, sustainability, Indian languages)

🏆 ACL’25 (Outstanding Paper), NAACL’24/’22, LREC’26

🙏 Grateful to @DrAnubhaGupta

🔬 Open to academic opportunities

#SpeechProcessing #ResponsibleAI #IIITD https://t.co/ejGp8zsWS8

2

0

176

Biswesh Mohapatra @bis1602

9 months ago

🎉 Happy to share that "SpeechMapper: Speech-to-text Embedding Projector for LLMs" has been accepted to #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

1

4

0

109

Yohei Kawaguchi @yohekawag

9 months ago

Three papers from our unit have been accepted to ICASSP 2026! See you in Barcelona for discussions! #ICASSP2026 #ICASSP #SignalProcessing #AI #SpeechProcessing

0

17

1

2K

yash @yashvarma_in

10 months ago

My first paper, “Attention Enhanced Speaker Representation with Contrastive Learning,” is now published at an IEEE Conference https://t.co/fRNEpPHtfu #FirstPublication #IEEE #MachineLearning #SpeechProcessing #ResearchJourney

2

4

0

90

DSP @uvic_DSP

12 months ago

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

0

2

0

38

SIRT BHOPAL @SIRT_BHOPAL

about 1 year ago

Huge congratulations to Dr. Shalini Sahay, Professor in the EC Department at SIRT, on publishing her book, "Optimization Analysis of Speech Processing Based Alzheimer's Disease." #BookPublished #AlzheimersResearch #SpeechProcessing #SIRT #ECEngineering

SIRT_BHOPAL's tweet photo. Huge congratulations to Dr. Shalini Sahay, Professor in the EC Department at SIRT, on publishing her book, "Optimization Analysis of Speech Processing Based Alzheimer's Disease."

#BookPublished #AlzheimersResearch #SpeechProcessing #SIRT #ECEngineering https://t.co/ogeWU6lXIp

0

2

1

0

71

Mirco Ravanelli @mirco_ravanelli

about 1 year ago

Tomorrow (Sept 25, 11:00–12:00 EST), our #ConversationalAI Reading Group hosts @Themos Stafylakis (Athens Univ. & Omilia). Talk: Advances in Speaker Recognition: Pruning, Deepfake Detection & Learning w/o Temporal Labels Info: https://t.co/idkmKuAYxi #AI #SpeechProcessing

0

4

0

449

MT Group at FBK @fbk_mt

over 1 year ago

Our pick of the week by @FBKZhihangXie: "Adversarial Speech-Text Pre-Training for Speech Translation" by Chenxuan Liu, Liping Chen, Weitai Zhang, Xiaoxi Li, Peiwang Tang, Mingjia Yu, Sreyan Ghosh, and Zhongyi Ye (ICASSP 2025) #speech #speechprocessing #speechtech #translation

Zhihang Xie @FBKZhihangXie

over 1 year ago

🚀 AdvST: Adversarial training aligns speech and text distributions without parallel data! Combines adversarial learning + hidden-state swapping to fix length mismatch & boost low-resource speech translation. https://t.co/l3V0trHD8m

0

3

0

284

0

3

0

233

ELOQUENCE AI @eloquenceai

over 1 year ago

📢 The Jelinek Summer Workshop on Speech and Language Technology (JSALT 2025) starts today! 👉 More info: https://t.co/9KkCIWPCUM #ELOQUENCEAI #SpeechProcessing #SpeechTechnology #Workshop

eloquenceai's tweet photo. 📢 The Jelinek Summer Workshop on Speech and Language Technology (JSALT 2025) starts today!

👉 More info: https://t.co/9KkCIWPCUM

#ELOQUENCEAI #SpeechProcessing #SpeechTechnology #Workshop https://t.co/z2Em2Euafz

0

5

0

34

Ehsan Eqlimi @ehsan_eqlimi

over 1 year ago

Excited to share our new paper in B-ENT Journal on how the brain responds to speech across different modalities (audiovisual, auditory, visual) using fNIRS! Explore the localization of cortical responses in normal-hearing adults #fNIRS #SpeechProcessing #Neuroimaging

1

0

455

MT Group at FBK @fbk_mt

over 1 year ago

Our pick of the week by @FBKZhihangXie: "Bridging Speech and Text Foundation Models with ReShape Attention" by @TakatomoKano, @chenwanch1, @shinjiw_at_cmu, et al. (#ICASSP2025) https://t.co/MuwEvCiUOJ #Speech #FoundationModel #SpeechProcessing

Zhihang Xie @FBKZhihangXie

over 1 year ago

ReShape Attention bridges speech & text models without extra parameters. Achieves +8.5% BLEU in translation by leveraging acoustic cues, outperforming cascade/E2E methods. Efficient & scalable. Check the paper by Kano et al. (2025) at: https://t.co/Z3kU7J0irM.

0

2

0

792

0

7

4

0

682

ILCB @ILCB_france

over 1 year ago

🧠🗣️ New research in eLife explores speech coordination & brain dynamics using intracranial recordings! Read more: https://t.co/N7ONEgV9zO #Neuroscience #SpeechProcessing #BrainDynamics

0

3

1

0

243

Dr. Teresa Lynn @cigilt

almost 2 years ago

Dr Hanan Aldarmaki of @mbzuai presenting her team’s research on #Arabic dialect #speechprocessing at COLING’s Arabic NLP Winter School in Abu Dhabi. What a great start to an exciting week! 💫 @nyhabash #coling2025

cigilt's tweet photo. Dr Hanan Aldarmaki of @mbzuai presenting her team’s research on #Arabic dialect #speechprocessing at COLING’s Arabic NLP Winter School in Abu Dhabi. What a great start to an exciting week! 💫 @nyhabash #coling2025 https://t.co/Oe9yY9G0V1

0

5

0

214

TTIC @TTIC_Connect

almost 2 years ago

Congratulations to Professor Karen Livescu on being named a 2025 IEEE Fellow! 🎉 Recognized for her pioneering work in multi-view & pre-trained speech representation learning, she continues to advance #speechprocessing & #AI. Read more: https://t.co/MkoIPMbMFh

TTIC_Connect's tweet photo. Congratulations to Professor Karen Livescu on being named a 2025 IEEE Fellow! 🎉 Recognized for her pioneering work in multi-view & pre-trained speech representation learning, she continues to advance #speechprocessing & #AI. Read more: https://t.co/MkoIPMbMFh https://t.co/fW3Z7cusLx

0

27

2

0

906

Francesc Alías Pujol @falias

almost 2 years ago

@luisjoglar @LaSalleBCN @uramonllull @mfreixesg and myself presenting the #BeNeXT and #FEMVoQ projects at the SpecialSession of #IberSPEECH2024 @LaSalleBCN @uramonllull #HER #speechprocessing

falias's tweet photo. @luisjoglar @LaSalleBCN @uramonllull @mfreixesg and myself presenting the #BeNeXT and #FEMVoQ projects at the SpecialSession of #IberSPEECH2024 @LaSalleBCN @uramonllull #HER #speechprocessing https://t.co/5h4CVoiqiz

1

6

2

0

201

Francesc Alías Pujol @falias

almost 2 years ago

@luisjoglar on the stage of #IberSPEECH2024, presenting our work related to the analysis of speech under #stress through glottal inverse filtering #FEMVoQ,#DISTRESIA #VOCE #speechprocessing #HER @LaSalleBCN @uramonllull #digitalhealth #voicebiomarkers

falias's tweet photo. @luisjoglar on the stage of #IberSPEECH2024, presenting our work related to the analysis of speech under #stress through glottal inverse filtering #FEMVoQ,#DISTRESIA #VOCE #speechprocessing #HER @LaSalleBCN @uramonllull #digitalhealth #voicebiomarkers https://t.co/xdPcwMhLky

1

5

1

0

130

Luis Joglar @luisjoglar

almost 2 years ago

Excited to be at #IberSPEECH24 presenting my research on Characterizing Speech Under Stress through Glottal Source Features using QCP. Catch my oral session tomorrow at 15h to learn more about it! #SpeechScience #SpeechProcessing @falias @LaSalleBCN https://t.co/qQXsHe9ymv

0

3

0

100