English
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어

#speechrecognition search results

PatentPulse's profile picture. Immerse yourself in the world of pioneering inventions with our curated collection of the most interesting and innovative recently published patent apps.
Interesting Patents
@PatentPulse
Nov 2

🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…

PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
0
0
0
0
60
sarthak_v2's profile picture. Associate Consultant @VMware Cloud, Docker Captain 🐳@Docker MVP | @CsharpCorner, @alibaba_cloud, MVB | Tutorials link @tutslink
Sarthak Varshney
 @sarthak_v2
Nov 12

🎙️ Noisy interviews? Rap songs? 11 languages? Qwen3 ASR handles it all—even singing with background music. Speech recognition built for the real world, not studios. Why this might be the breakthrough 👇 c-sharpcorner.com/article/qwen3-… by @sarthak_v2 via @CsharpCorner #SpeechRecognition

sarthak_v2's tweet image. 🎙️ Noisy interviews? Rap songs? 11 languages? Qwen3 ASR handles it all—even singing with background music. Speech recognition built for the real world, not studios. Why this might be the breakthrough 👇 c-sharpcorner.com/article/qwen3-… by @sarthak_v2 via @CsharpCorner #SpeechRecognition
1
0
3
0
38
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
May 23

speech_recognition Power your Python projects with speech recognition! This library supports 15+ engines & APIs, including Google Cloud Speech API & OpenAI Whisper. #speechrecognition #python

D4Vinci1's tweet image. speech_recognition Power your Python projects with speech recognition! This library supports 15+ engines & APIs, including Google Cloud Speech API & OpenAI Whisper. #speechrecognition #python
1
0
3
1
69
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
May 16

moshi Introducing Moshi: a speech-text foundation model for real-time dialogue! Talk to Moshi, a full-duplex AI that can understand your inner monologue. Learn more about this innovative tech [link] #AI #SpeechRecognition

D4Vinci1's tweet image. moshi Introducing Moshi: a speech-text foundation model for real-time dialogue! Talk to Moshi, a full-duplex AI that can understand your inner monologue. Learn more about this innovative tech [link] #AI #SpeechRecognition
1
0
2
0
81
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
Jul 6

voice-pro Transform multimedia content creation with Voice-Pro, a web app for AI-powered speech recognition, translation, and dubbing, featuring top-tier speech recognition, zero-shot voice cloning, and multilingual text-to-speech. #VoicePro #AI #SpeechRecognition

D4Vinci1's tweet image. voice-pro Transform multimedia content creation with Voice-Pro, a web app for AI-powered speech recognition, translation, and dubbing, featuring top-tier speech recognition, zero-shot voice cloning, and multilingual text-to-speech. #VoicePro #AI #SpeechRecognition
1
0
3
1
101
ProceedingsIEEE's profile picture. The leading journal to provide reviews, surveys, and tutorials on technical developments in electronics, electrical engineering, and computer science.
Proceedings of the IEEE
 @ProceedingsIEEE
Sep 25

From #SpeechRecognition to sound event detection, machines are learning to listen. #ComputerAudition is moving from single-task tools to powerful, multitasking foundation models. Learn more in a new article published in @ProceedingsIEEE's April 2025 issue: bit.ly/ProceedingsIEE…

ProceedingsIEEE's tweet image. From #SpeechRecognition to sound event detection, machines are learning to listen. #ComputerAudition is moving from single-task tools to powerful, multitasking foundation models. Learn more in a new article published in @ProceedingsIEEE's April 2025 issue: bit.ly/ProceedingsIEE…
0
0
0
0
45
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
Aug 17

wenet Introducing WeNet, a production-ready, lightweight, and accurate ASR (Automatic Speech Recognition) model. Transcribe audio with ease using Python! #WeNet #ASR #SpeechRecognition

D4Vinci1's tweet image. wenet Introducing WeNet, a production-ready, lightweight, and accurate ASR (Automatic Speech Recognition) model. Transcribe audio with ease using Python! #WeNet #ASR #SpeechRecognition
1
0
1
0
152
PyImageSearch's profile picture. Leading deep learning educator. Tutorials and courses on #DeepLearning, #ComputerVision, #LLMs, #GenAI, #OpenCV, #Keras, #TensorFlow, #PyTorch, and many more.
PyImageSearch
 @PyImageSearch
Nov 17

Could one AI model eventually understand every spoken language? Meta's new Omnilingual ASR project is a fascinating step in that direction. Check out their approach to this massive challenge. What are the implications? ai.meta.com/blog/omnilingu… #AI #SpeechRecognition

PyImageSearch's tweet image. Could one AI model eventually understand every spoken language? Meta's new Omnilingual ASR project is a fascinating step in that direction. Check out their approach to this massive challenge. What are the implications? ai.meta.com/blog/omnilingu… #AI #SpeechRecognition
0
0
2
2
451
geetpurwar's profile picture. Post about latest AI news, tools, tutorials and memes.
Geet Purwar
@geetpurwar
Sep 17

🎉 Woohoo! We’ve fixed the Whisper hallucination issue when no one’s speaking — thanks to Apple’s in-built speech detection 🗣️✨ Now silence stays silent, and transcripts stay clean. 🚀 Retweet & Reply "Doggy" if you want access! #ai #whisper #speechRecognition

geetpurwar's tweet image. 🎉 Woohoo! We’ve fixed the Whisper hallucination issue when no one’s speaking — thanks to Apple’s in-built speech detection 🗣️✨ Now silence stays silent, and transcripts stay clean. 🚀 Retweet & Reply "Doggy" if you want access! #ai #whisper #speechRecognition
1
0
2
0
123
PatentPulse's profile picture. Immerse yourself in the world of pioneering inventions with our curated collection of the most interesting and innovative recently published patent apps.
Interesting Patents
@PatentPulse
Sep 26

New patent application #US20250299678A1 by #Meta introduces advanced #SpeechRecognition tech. It uses multi-path acoustic echo cancellation and beamforming to refine audio from multiple microphones, enabling accurate speech-to-text transcription. #AI $META

PatentPulse's tweet image. New patent application #US20250299678A1 by #Meta introduces advanced #SpeechRecognition tech. It uses multi-path acoustic echo cancellation and beamforming to refine audio from multiple microphones, enabling accurate speech-to-text transcription. #AI $META
PatentPulse's tweet image. New patent application #US20250299678A1 by #Meta introduces advanced #SpeechRecognition tech. It uses multi-path acoustic echo cancellation and beamforming to refine audio from multiple microphones, enabling accurate speech-to-text transcription. #AI $META
PatentPulse's tweet image. New patent application #US20250299678A1 by #Meta introduces advanced #SpeechRecognition tech. It uses multi-path acoustic echo cancellation and beamforming to refine audio from multiple microphones, enabling accurate speech-to-text transcription. #AI $META
0
0
0
0
55
soketlabs's profile picture. Soket Labs is an AI research firm with a vision to further the advancement in AI towards ethical AGI.
Soket AI
 @soketlabs
Nov 12

Announcing CoSHE-Eval — a Hindi–English code-switching ASR evaluation benchmark from Soket AI Labs. 30 hours of curated, human-verified bilingual speech for ASR evaluation. Read more soket.ai/blogs/coshe_ev… Dataset → huggingface.co/datasets/soket… #ASR #SpeechRecognition

soketlabs's tweet card. soketlabs/CoSHE-Eval · Datasets at Hugging Face
soketlabs/CoSHE-Eval · Datasets at Hugging Face
Source: huggingface.co
1
2
3
1
141
telnyx's profile picture. 🤝 Your connectivity partner 🤝 Build custom voice and connectivity with Telnyx Voice AI, Voice API, and eSIMs. Full-stack power without the patchwork.
Telnyx
@telnyx
Oct 8

STT that actually keeps up with real-time voice 🎙️⚡️ We just expanded our @DeepgramAI integration to Telnyx Voice API + TeXML! This means enterprise-grade transcription in 30+ languages, ready for production A quick thread 🧵 ↓ #VoiceAI #DevTools #SpeechRecognition

1
1
1
0
141
CursedCompani0n's profile picture. If we say the wrong words... WE DIE! This game kills you with your own voices! Co-op where everyone gets a forbidden word, say it and you kill your friend!
Cursed Companions | 🔥Launching on 20 Nov 2025 !
@CursedCompani0n
Nov 28

Pay respects to the Dark Queen👑at her shrine. Say 'We Live to Serve' and you are granted an audience! Then you can ask for treasure🏆, or healing and more! The game listens to what you and your friends say. 👄 #indiegame #horrorgame #speechrecognition #gamedev

2
0
11
0
281
DrClaireH's profile picture. Active account: https://t.co/koiR69nNZF
Prof Claire Hardaker (dormant account)
 @DrClaireH
Oct 4, 2024

1/4 🤖 Remember when we did Bot or Not: Text Edition? Guess what? With thanks to Hope McVean, @GeorgebrownLing and I have just launched the essential follow-up - Bot or Not: Audio Edition. 🤩 Can you distinguish between humans and AI just by listening? #AI #SpeechRecognition

DrClaireH's tweet image. 1/4 🤖 Remember when we did Bot or Not: Text Edition? Guess what? With thanks to Hope McVean, @GeorgebrownLing and I have just launched the essential follow-up - Bot or Not: Audio Edition. 🤩 Can you distinguish between humans and AI just by listening? #AI #SpeechRecognition
1
5
13
3
3K
_kedar_18's profile picture. BTech student | ML Enthusiast | Diplomacy Buff | CSE' 27 | https://t.co/cWsj6pUGWf | 🙇@imVkohli
kedar
@_kedar_18
Sep 4

Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship

_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
3
0
17
0
224
androidPonsel_'s profile picture. Tech nerd: Android, gadget, EV | News & tips | GASS! #TechUpdate
androidponsel.com
@androidPonsel_
Jul 3

MediaTek rilis MR BreezeASR 25, model AI open-source yang dirancang khusus untuk bahasa & aksen Taiwan. Akurasi meningkat 10% dari Whisper, cocok untuk aplikasi AI lokal. 🔗 Selengkapnya: androidponsel.com/mr-breezeasr-2… #AI #MediaTek #SpeechRecognition

androidPonsel_'s tweet image. MediaTek rilis MR BreezeASR 25, model AI open-source yang dirancang khusus untuk bahasa & aksen Taiwan. Akurasi meningkat 10% dari Whisper, cocok untuk aplikasi AI lokal. 🔗 Selengkapnya: androidponsel.com/mr-breezeasr-2… #AI #MediaTek #SpeechRecognition
0
0
0
0
220
AppMarketPlus's profile picture. Professional PR & App Promotion agency. Promote your iPhone, Android apps with us #appmarketing #apppromotion #appreviews
App Marketing Plus
 @AppMarketPlus
Nov 3

Stop typing — start speaking! 🎤✨ Check out the best voice-to-text apps for accurate, hands-free productivity. From Otter.ai to Google Voice Typing, we reviewed them all 👇 🔗 apps4review.com/best-voice-to-… #VoiceToText #AIApps #SpeechRecognition

AppMarketPlus's tweet image. Stop typing — start speaking! 🎤✨ Check out the best voice-to-text apps for accurate, hands-free productivity. From Otter.ai to Google Voice Typing, we reviewed them all 👇 🔗 apps4review.com/best-voice-to-… #VoiceToText #AIApps #SpeechRecognition
0
0
0
0
9
discvrai's profile picture. 🚀 https://t.co/MqSrr2TiZP | Global fintech disruptor. Latest market news. AI powered research for Stocks, Funds, Crypto & US markets. Smarter portfolios, everywhere.
DiscvrAI
@discvrai
Nov 19

🌍 Meta’s new speech-to-text AI supports 1,600 languages 🎙️ Focus on low-resource dialects = better global accessibility 📚 Use cases: education, civic services, cross-border communication discvr.ai/latestnews/ai/… #AI #Meta #SpeechRecognition #Accessibility #TechNews #Innovation

discvrai's tweet card. Meta launches speech-to-text AI for 1,600 languages, advancing global accessibility and transcription accuracy.
Meta Expands Speech Recognition to 1,600 Languages | Discvr Financial News
Source: discvr.ai
0
0
0
0
16
PyImageSearch's profile picture. Leading deep learning educator. Tutorials and courses on #DeepLearning, #ComputerVision, #LLMs, #GenAI, #OpenCV, #Keras, #TensorFlow, #PyTorch, and many more.
PyImageSearch
 @PyImageSearch
Nov 17

Could one AI model eventually understand every spoken language? Meta's new Omnilingual ASR project is a fascinating step in that direction. Check out their approach to this massive challenge. What are the implications? ai.meta.com/blog/omnilingu… #AI #SpeechRecognition

PyImageSearch's tweet image. Could one AI model eventually understand every spoken language? Meta's new Omnilingual ASR project is a fascinating step in that direction. Check out their approach to this massive challenge. What are the implications? ai.meta.com/blog/omnilingu… #AI #SpeechRecognition
0
0
2
2
451
Applsci's profile picture. Applied Sciences (ISSN 2076-3417; IF 2.5) is an international peer-reviewed #openaccess journal on all aspects of applied natural sciences by @MDPIOpenAccess.
Applied Sciences MDPI
@Applsci
Nov 17

📢 #SpecialIssue Advanced Human–AI Interaction: Speech and Natural Language Processing 📅 20 April 2026 👨‍🔬 Guest Editor: Dr. Carlos Delgado from University of Alcala, Spain 🔗 mdpi.com/journal/applsc… #naturallanguageprocessing #speechrecognition #humancomputerinteraction…

Applsci's tweet image. 📢 #SpecialIssue Advanced Human–AI Interaction: Speech and Natural Language Processing 📅 20 April 2026 👨‍🔬 Guest Editor: Dr. Carlos Delgado from University of Alcala, Spain 🔗 mdpi.com/journal/applsc… #naturallanguageprocessing #speechrecognition #humancomputerinteraction…
0
0
2
0
60
_DSEDU's profile picture. A leading distributor with a focus on educational resources and tech. | Web: https://t.co/RGug5e8e3Q | Call: +44 (0) 1252 619829
Douglas Stewart EDU
 @_DSEDU
Nov 14

💻 Empower productivity with Nuance Assistive Technology! 🚀 From speech recognition to advanced dictation tools, discover solutions designed to transform how you work and communicate. bit.ly/3zJ5M43 #AssistiveTech #Nuance #SpeechRecognition #WorkSmart

_DSEDU's tweet image. 💻 Empower productivity with Nuance Assistive Technology! 🚀 From speech recognition to advanced dictation tools, discover solutions designed to transform how you work and communicate. bit.ly/3zJ5M43 #AssistiveTech #Nuance #SpeechRecognition #WorkSmart
0
0
0
0
14
voicegenie_ai's profile picture. Voice AI Agents for Sales, Support & Operations
VoiceGenie
@voicegenie_ai
Nov 14

How Does Speech Recognition Work In Voice AI Agents #speechrecognition #voiceai #aiagents #conversationalai #automation

0
0
1
0
15
ernesttheaiguy's profile picture. Founder & CEO, The Data Experts | Engineer | SecOps | AI | Gray Jedi | Change Management Expert
Ernest Provo
@ernesttheaiguy
Nov 12

meta ai's omnilingual ASR covers 1600+ languages, tackling speech recognition for underserved tongues. impressive scale, but real-world deployment in noisy enterprise settings remains unproven. thoughts? marktechpost.com/2025/11/11/met…... #AI #SpeechRecognition

ernesttheaiguy's tweet card. Meta AI Releases Omnilingual ASR: A Suite of Open-Source Multilingual Speech Recognition Models for 1600+ Languages
Meta AI Releases Omnilingual ASR: A Suite of Open-Source Multilingual Speech Recognition Models for...
Source: marktechpost.com
0
0
0
0
24
sarthak_v2's profile picture. Associate Consultant @VMware Cloud, Docker Captain 🐳@Docker MVP | @CsharpCorner, @alibaba_cloud, MVB | Tutorials link @tutslink
Sarthak Varshney
 @sarthak_v2
Nov 12

🎙️ Noisy interviews? Rap songs? 11 languages? Qwen3 ASR handles it all—even singing with background music. Speech recognition built for the real world, not studios. Why this might be the breakthrough 👇 c-sharpcorner.com/article/qwen3-… by @sarthak_v2 via @CsharpCorner #SpeechRecognition

sarthak_v2's tweet image. 🎙️ Noisy interviews? Rap songs? 11 languages? Qwen3 ASR handles it all—even singing with background music. Speech recognition built for the real world, not studios. Why this might be the breakthrough 👇 c-sharpcorner.com/article/qwen3-… by @sarthak_v2 via @CsharpCorner #SpeechRecognition
1
0
3
0
38
soketlabs's profile picture. Soket Labs is an AI research firm with a vision to further the advancement in AI towards ethical AGI.
Soket AI
 @soketlabs
Nov 12

Announcing CoSHE-Eval — a Hindi–English code-switching ASR evaluation benchmark from Soket AI Labs. 30 hours of curated, human-verified bilingual speech for ASR evaluation. Read more soket.ai/blogs/coshe_ev… Dataset → huggingface.co/datasets/soket… #ASR #SpeechRecognition

soketlabs's tweet card. soketlabs/CoSHE-Eval · Datasets at Hugging Face
soketlabs/CoSHE-Eval · Datasets at Hugging Face
Source: huggingface.co
1
2
3
1
141
MarkFree1058358's profile picture.
Mark Free
 @MarkFree1058358
Nov 12

Raw audio's messy! Feature extraction (like MFCCs) cuts noise, keeps speech essence so machines understand words. #SpeechRecognition #AI milvus.io/ai-quick-refer…

0
0
0
0
16
MarkFree1058358's profile picture.
Mark Free
 @MarkFree1058358
Nov 12

Optimize speech recognition: track WER, latency, robustness to ensure great voice tech. #SpeechRecognition #DevTips milvus.io/ai-quick-refer…

0
0
0
0
5
simpaisush's profile picture. Data Scientist & AI Engineer | e-acc | technologia | Nature Lover | @promptsgen_ai | funny - serious combo | No DM | 🧊| 🐙 | Λ⚡ø | @X | available for hiring 💰
_simpaisush🤓
 @simpaisush
Nov 11

Meta AI unveils Omnilingual ASR! 🗣️🌍 Transcribes 1600+ languages, including low-resource ones, with impressive accuracy. Built on wav2vec 2.0, it offers ZST and supports endangered languages. A game-changer for global communication! #AI #SpeechRecognition #Language

0
0
1
0
30
_DSEDU's profile picture. A leading distributor with a focus on educational resources and tech. | Web: https://t.co/RGug5e8e3Q | Call: +44 (0) 1252 619829
Douglas Stewart EDU
 @_DSEDU
Nov 8

💻 Empower productivity with Nuance Assistive Technology! 🚀 From speech recognition to advanced dictation tools, discover solutions designed to transform how you work and communicate. bit.ly/3zJ5M43 #AssistiveTech #Nuance #SpeechRecognition #WorkSmart

_DSEDU's tweet image. 💻 Empower productivity with Nuance Assistive Technology! 🚀 From speech recognition to advanced dictation tools, discover solutions designed to transform how you work and communicate. bit.ly/3zJ5M43 #AssistiveTech #Nuance #SpeechRecognition #WorkSmart
0
0
0
0
14
ieee_asru's profile picture. IEEE ASRU, is focused on bringing together academia and industry to discuss new developments on the field of Automatic Speech Recognition and Understanding.
IEEE ASRU
 @ieee_asru
Nov 7

✨ Thank you to our gold sponsor, JPMorgan Chase, for your generous support of IEEE ASRU 2025! We’re looking forward to a successful conference thanks to your support! 🔗 2025.ieeeasru.org/sponsors/spons… #SpeechRecognition #Hawaii #ArtificialIntelligence @IEEEsps

0
0
0
0
53
PatentPulse's profile picture. Immerse yourself in the world of pioneering inventions with our curated collection of the most interesting and innovative recently published patent apps.
Interesting Patents
@PatentPulse
Nov 2

🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…

PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
PatentPulse's tweet image. 🚀 New patent application alert: #US20250335739A1 by #Google. Discover how Convolution-Augmented Transformer Models enhance data processing tasks like #SpeechRecognition, sound separation, and #NLP. This innovative conformer model integrates feed-forward, self-attention, and…
0
0
0
0
60
ProceedingsIEEE's profile picture. The leading journal to provide reviews, surveys, and tutorials on technical developments in electronics, electrical engineering, and computer science.
Proceedings of the IEEE
 @ProceedingsIEEE
Sep 25

From #SpeechRecognition to sound event detection, machines are learning to listen. #ComputerAudition is moving from single-task tools to powerful, multitasking foundation models. Learn more in a new article published in @ProceedingsIEEE's April 2025 issue: bit.ly/ProceedingsIEE…

ProceedingsIEEE's tweet image. From #SpeechRecognition to sound event detection, machines are learning to listen. #ComputerAudition is moving from single-task tools to powerful, multitasking foundation models. Learn more in a new article published in @ProceedingsIEEE's April 2025 issue: bit.ly/ProceedingsIEE…
0
0
0
0
45
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
May 23

speech_recognition Power your Python projects with speech recognition! This library supports 15+ engines & APIs, including Google Cloud Speech API & OpenAI Whisper. #speechrecognition #python

D4Vinci1's tweet image. speech_recognition Power your Python projects with speech recognition! This library supports 15+ engines & APIs, including Google Cloud Speech API & OpenAI Whisper. #speechrecognition #python
1
0
3
1
69
LyngualLabs's profile picture.
LyngualLabs
 @LyngualLabs
Aug 19

Thrilled to share our paper on multilingual ASR for code-switched Yoruba-English speech was accepted at @DeepIndaba #LyngualLabs #LowResourceAI #SpeechRecognition #DLI2025

LyngualLabs's tweet image. Thrilled to share our paper on multilingual ASR for code-switched Yoruba-English speech was accepted at @DeepIndaba #LyngualLabs #LowResourceAI #SpeechRecognition #DLI2025
LyngualLabs's tweet image. Thrilled to share our paper on multilingual ASR for code-switched Yoruba-English speech was accepted at @DeepIndaba #LyngualLabs #LowResourceAI #SpeechRecognition #DLI2025
2
11
23
1
2K
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
May 16

moshi Introducing Moshi: a speech-text foundation model for real-time dialogue! Talk to Moshi, a full-duplex AI that can understand your inner monologue. Learn more about this innovative tech [link] #AI #SpeechRecognition

D4Vinci1's tweet image. moshi Introducing Moshi: a speech-text foundation model for real-time dialogue! Talk to Moshi, a full-duplex AI that can understand your inner monologue. Learn more about this innovative tech [link] #AI #SpeechRecognition
1
0
2
0
81
geetpurwar's profile picture. Post about latest AI news, tools, tutorials and memes.
Geet Purwar
@geetpurwar
Sep 17

🎉 Woohoo! We’ve fixed the Whisper hallucination issue when no one’s speaking — thanks to Apple’s in-built speech detection 🗣️✨ Now silence stays silent, and transcripts stay clean. 🚀 Retweet & Reply "Doggy" if you want access! #ai #whisper #speechRecognition

geetpurwar's tweet image. 🎉 Woohoo! We’ve fixed the Whisper hallucination issue when no one’s speaking — thanks to Apple’s in-built speech detection 🗣️✨ Now silence stays silent, and transcripts stay clean. 🚀 Retweet & Reply "Doggy" if you want access! #ai #whisper #speechRecognition
1
0
2
0
123
foan82's profile picture. UX Design Director & AI Researcher
Foan82
 @foan82
May 17, 2023

The easiest way to convert messy thoughts into clear text. Just hit record. Then start rambling. AudioPen will clean things up when you're done. Price: Fremium Source: Audiopen(.)ai #ai #speechrecognition #speaker #speechtotext #audiopen #futuretools #foan82

foan82's tweet image. The easiest way to convert messy thoughts into clear text. Just hit record. Then start rambling. AudioPen will clean things up when you're done. Price: Fremium Source: Audiopen(.)ai #ai #speechrecognition #speaker #speechtotext #audiopen #futuretools #foan82
0
2
2
1
627
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
Jul 6

voice-pro Transform multimedia content creation with Voice-Pro, a web app for AI-powered speech recognition, translation, and dubbing, featuring top-tier speech recognition, zero-shot voice cloning, and multilingual text-to-speech. #VoicePro #AI #SpeechRecognition

D4Vinci1's tweet image. voice-pro Transform multimedia content creation with Voice-Pro, a web app for AI-powered speech recognition, translation, and dubbing, featuring top-tier speech recognition, zero-shot voice cloning, and multilingual text-to-speech. #VoicePro #AI #SpeechRecognition
1
0
3
1
101
D4Vinci1's profile picture. A Pythonista 🐍 | CS/InfoSec lover | Web Scraping Expert. Author of many known projects like @Scrapling_dev Follow for posts about interesting GitHub repos...
Karim Shoair
 @D4Vinci1
Aug 17

wenet Introducing WeNet, a production-ready, lightweight, and accurate ASR (Automatic Speech Recognition) model. Transcribe audio with ease using Python! #WeNet #ASR #SpeechRecognition

D4Vinci1's tweet image. wenet Introducing WeNet, a production-ready, lightweight, and accurate ASR (Automatic Speech Recognition) model. Transcribe audio with ease using Python! #WeNet #ASR #SpeechRecognition
1
0
1
0
152
_kedar_18's profile picture. BTech student | ML Enthusiast | Diplomacy Buff | CSE' 27 | https://t.co/cWsj6pUGWf | 🙇@imVkohli
kedar
@_kedar_18
Sep 4

Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship

_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
_kedar_18's tweet image. Day 9 of my internship: Today I focused on Exploratory Data Analysis for my speech recognition project. Visualized waveforms and spectrograms Gained insights into audio patterns for fear, happy, and neutral speech. #DataScience #ML #SpeechRecognition #Internship
3
0
17
0
224
androidPonsel_'s profile picture. Tech nerd: Android, gadget, EV | News & tips | GASS! #TechUpdate
androidponsel.com
@androidPonsel_
Jul 3

MediaTek rilis MR BreezeASR 25, model AI open-source yang dirancang khusus untuk bahasa & aksen Taiwan. Akurasi meningkat 10% dari Whisper, cocok untuk aplikasi AI lokal. 🔗 Selengkapnya: androidponsel.com/mr-breezeasr-2… #AI #MediaTek #SpeechRecognition

androidPonsel_'s tweet image. MediaTek rilis MR BreezeASR 25, model AI open-source yang dirancang khusus untuk bahasa & aksen Taiwan. Akurasi meningkat 10% dari Whisper, cocok untuk aplikasi AI lokal. 🔗 Selengkapnya: androidponsel.com/mr-breezeasr-2… #AI #MediaTek #SpeechRecognition
0
0
0
0
220
NVIDIAAIDev's profile picture. All things AI for developers from @NVIDIA. Additional developer channels: @NVIDIADeveloper, @NVIDIAHPCDev, and @NVIDIAGameDev.
NVIDIA AI Developer
@NVIDIAAIDev
Feb 6, 2024

Looking for lightning-fast #ASR? Check out NVIDIA NeMo Parakeet-TDT. The open-source model is #1 on the @HuggingFace Open ASR Leaderboard and is 64% faster than the previous best model. #SpeechRecognition #AI ⚡ nvda.ws/3SxaVBs

NVIDIAAIDev's tweet image. Looking for lightning-fast #ASR? Check out NVIDIA NeMo Parakeet-TDT. The open-source model is #1 on the @HuggingFace Open ASR Leaderboard and is 64% faster than the previous best model. #SpeechRecognition #AI ⚡ nvda.ws/3SxaVBs
35
33
166
53
25K
CUUttarPradesh's profile picture. Chandigarh University, Uttar Pradesh - India’s First AI Augmented Multidisciplinary University
Chandigarh University UP
@CUUttarPradesh
May 25

Ever wonder what powers smart speakers, voice assistants, and real-time transcription apps? Let's take today's #TechConnectQuiz to see how much you know about technology! Leave a comment with your response. #AI #SpeechRecognition #DeepLearning #MachineLearning #EdTech…

CUUttarPradesh's tweet image. Ever wonder what powers smart speakers, voice assistants, and real-time transcription apps? Let's take today's #TechConnectQuiz to see how much you know about technology! Leave a comment with your response. #AI #SpeechRecognition #DeepLearning #MachineLearning #EdTech…
1
0
3
1
113
LelapaAI's profile picture. Resource-efficient AI from Africa to the World.
Lelapa AI
 @LelapaAI
Mar 19

Big Tech loves using African data. But do African communities benefit? Let’s talk about a new framework that changes the game 🎙️👇 - T H R E A D - #AfricanAI #MultilingualAI #SpeechRecognition #EthicalAI #DataForGood #TechForAfrica #LanguageEquity #AIForAll

LelapaAI's tweet image. Big Tech loves using African data. But do African communities benefit? Let’s talk about a new framework that changes the game 🎙️👇 - T H R E A D - #AfricanAI #MultilingualAI #SpeechRecognition #EthicalAI #DataForGood #TechForAfrica #LanguageEquity #AIForAll
3
1
3
1
302
PatentPulse's profile picture. Immerse yourself in the world of pioneering inventions with our curated collection of the most interesting and innovative recently published patent apps.
Interesting Patents
@PatentPulse
Sep 8

📢 New patent application #US20250278240A1 by #Google explores #SpeechRecognition using active acoustic sensing. A hearable device uses ultrasound signals in the ear canal to capture speech and muscle movements, enhancing recognition accuracy. This method fuses ultrasound data…

PatentPulse's tweet image. 📢 New patent application #US20250278240A1 by #Google explores #SpeechRecognition using active acoustic sensing. A hearable device uses ultrasound signals in the ear canal to capture speech and muscle movements, enhancing recognition accuracy. This method fuses ultrasound data…
PatentPulse's tweet image. 📢 New patent application #US20250278240A1 by #Google explores #SpeechRecognition using active acoustic sensing. A hearable device uses ultrasound signals in the ear canal to capture speech and muscle movements, enhancing recognition accuracy. This method fuses ultrasound data…
PatentPulse's tweet image. 📢 New patent application #US20250278240A1 by #Google explores #SpeechRecognition using active acoustic sensing. A hearable device uses ultrasound signals in the ear canal to capture speech and muscle movements, enhancing recognition accuracy. This method fuses ultrasound data…
0
0
1
0
78
bitlauncherai's profile picture. Crowdfunding platform for Ai startups (non-US investors only) #Ai / #web3 Powered by https://t.co/P3vUXMFUCw
bitlauncher
@bitlauncherai
Jun 8, 2024

🔥 Unleash the power of #LargeLanguageModels to transform text into spoken magic! 🎙️ #NaturalLanguageProcessing #SpeechRecognition #AI🧵👇

bitlauncherai's tweet image. 🔥 Unleash the power of #LargeLanguageModels to transform text into spoken magic! 🎙️ #NaturalLanguageProcessing #SpeechRecognition #AI🧵👇
1
0
0
0
37
inexture's profile picture. Inexture is a top-rated #AI #python & #java development company. We work with SMEs since 2014 providing #web, mobile #app & enterprise #software services.
Inexture Solutions
 @inexture
Oct 14

Your voice holds business intelligence. We help you unlock it. ✔ Live meeting transcription ✔ Voice-enabled enterprise tools ✔ Industry-specific ASR models 👉 inexture.ai #ArtificialIntelligence #VoiceAI #SpeechRecognition #InextureSolutions #TechForBusiness

inexture's tweet image. Your voice holds business intelligence. We help you unlock it. ✔ Live meeting transcription ✔ Voice-enabled enterprise tools ✔ Industry-specific ASR models 👉 inexture.ai #ArtificialIntelligence #VoiceAI #SpeechRecognition #InextureSolutions #TechForBusiness
0
0
0
0
15

Something went wrong.


Something went wrong.


United States Trends