2026-07-19 01:45:46
whisper - brooke wheeler
#music
whisper - brooke wheeler
#music
Delhi High Court quashes the case against NewsClick on foreign funding, saying investigators failed to establish cheating, conspiracy, or any scheduled offense (The News Minute)
https://www.thenewsminute.com/news/not-a-w
OpenAI: Neue Audio-Modelle für Echtzeit-KI-Support
OpenAI bringt drei neue Audio-Modelle für die API: GPT-Realtime-2 für Echtzeit-Gespräche, Translate für Übersetzungen und Whisper für Live-Transkription.
https://www.
🇺🇦 #NowPlaying on KEXP's #VarietyMix
The Icicle Works:
🎵 Birds Fly (Whisper to a Scream)
#TheIcicleWorks
https://celebrationsummer.bandcamp.com/track/birds-fly-whisper-to-a-scream-the-icicle-works
https://open.spotify.com/track/2TZumdpLCbAnOtKfGzeSHf
We saw some geese with a cute gosling 🐤, went up the hill to enjoy the view, and did a little pedal boat tour across the lake.
Plus, we discovered a "Flüsterbrücke" ("whisper bridge"):
https://www.dortmund.de/themen/freizeit-un…
<sexy whisper>Landy!</sexy whisper>
#LandRover #YouTube
Sometimes I’ll click on your profile picture to make it bigger and whisper to myself “Well hello you little Fediverse cutie…”
James Talarico: Donald Trump voters 'whisper' support for him 'like they're in ... witness protection'
https://thehill.com/homenews/campaign/5897756-talarico-trump-texas-senate-race/
A lovely cooling Word of the Day for those of us in heatwaves...
psithurism
PRONUNCIATION:
(SITH-yuh-riz-uhm)
MEANING:
noun: A rustling or whispering sound, especially of leaves in the wind.
ETYMOLOGY:
From Greek psithurizein (to whisper), from psithuros (whispering, slanderous). Earliest documented use: 1848.
https:/…
Crosslisted article(s) found for eess.AS. https://arxiv.org/list/eess.AS/new
[1/1]:
- ShipEcho -- An Interactive Tool for Global Mapping of Underwater Radiated Noise from Vessels
Mark Shipton, Valentino Denona, {\DJ}ula Na{\dj}, Roee Diamant
https://arxiv.org/abs/2605.08194 https://mastoxiv.page/@arXiv_csSD_bot/116560461888286028
- Bangla-WhisperDiar: Fine-Tuning Whisper and PyAnnote for Bangla Long-Form Speech Recognition and ...
Bhuiyan, Adib, Bhuiyan, Chakraborty, Saswato, Dhrubo, Khan
https://arxiv.org/abs/2605.08214 https://mastoxiv.page/@arXiv_csSD_bot/116560470901569776
- Dolphin-CN-Dialect: Where Chinese Dialects Matter
Meng, Zhong, Lin, Wang, Du, Shao, Huang, Li, Zhang
https://arxiv.org/abs/2605.08961
- How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue
Hui Lu, Xueyuan Chen, Huimeng Wang, Shuhai Peng, Shiyin Kang, Xixin Wu, Zhiyong Wu
https://arxiv.org/abs/2605.10199
- Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibr...
Haowen Li, Tianxiang Li, Yi Yang, Boyu Cao, Qi Liu
https://arxiv.org/abs/2605.10203 https://mastoxiv.page/@arXiv_csSD_bot/116560575501371296
- Probing Cross-modal Information Hubs in Audio-Visual LLMs
Jihoo Jung, Chaeyoung Jung, Ji-Hoon Kim, Joon Son Chung
https://arxiv.org/abs/2605.10815 https://mastoxiv.page/@arXiv_csAI_bot/116560938059845601
toXiv_bot_toot
🇺🇦 #NowPlaying on KEXP's #SonicReducer
Code Blue:
🎵 Whisper / Touch
#CodeBlue
https://open.spotify.com/track/7czhD72Vh0W1XOvbvHa8bC
Whisper Doll - Am I A Knife (Official Video)
#music
🇺🇦 #NowPlaying on #BBC6Music's #6MusicArtistCollection
The Gossip:
🎵 Careless Whisper (Live)
#TheGossip
https://open.spotify.com/track/1dkLQCendgMOB6aXRRHWLx
Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models
Wei-Ping Huang, Chee-En Yu, Guan-Ting Lin, Hung-yi Lee
https://arxiv.org/abs/2605.08186 https://arxiv.org/pdf/2605.08186 https://arxiv.org/html/2605.08186
arXiv:2605.08186v1 Announce Type: new
Abstract: Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoretically fragmented. Existing approaches typically rely on distinct heuristics, such as teacher forcing with pseudo labels or policy-gradient-based reinforcement learning, without a unified mathematical foundation. In this work, we resolve this discrepancy by deriving a rigorous formulation of EM tailored to autoregressive models. We show that the exact objective naturally decomposes into a token-level policy gradient loss and a token-level entropy loss, and we reinterpret prior methods as partial realizations of this unified formulation. Using Whisper ASR as a testbed, we demonstrate that our approach consistently improves performance across more than 20 diverse domains, including acoustic noise, accents, and multilingual settings.
toXiv_bot_toot
🇺🇦 #NowPlaying on BBCRadio3's #ClassicalMixtape
Thomas Newman, Orchestra & Thomas Newman:
🎵 Meet Joe Black: Whisper of a Thrill
#ThomasNewman #Orchestra
https://open.spotify.com/track/7KGPlP1RyvOaq9Zl9jlBMA
🇺🇦 #NowPlaying on #BBC6Music's #CraigCharles
Cecile Campbell:
🎵 Whisper to Me
#CecileCampbell
https://open.spotify.com/track/5xgPgAWIZHRdXJsSlJdgJp