← Back← Announcements

From the source

Other stories

AI lab announcements, news reports and podcasts.

Announcements Chatter About Privacy Connect RSS

© 2026 forck.live

← Back← Announcements

From the source

Other stories

Measuring benchmark optimization in speech recognition — forck

← Back← Announcements

Copy▾✕ Close copy menu

Hume· 21 Aug

Measuring benchmark optimization in speech recognition

Research paper

Hugging Face and Hume logos — Image from hume.ai

From the source
New research introduces three tests to quantify benchmark optimization in speech recognition, finding top open-source ASR models reproduce benchmark transcripts even when the audio contradicts them.
hume.ai

Announced: 21 Aug 2026 14:00 UTC
First seen by forck: 03 Sep 2026 14:38 UTC (+13d after)

Visit source ↗

Other stories

Hume· 6 Oct

Behind Hume’s Expression Measurement Models for Face and Voice

How Hume's Expression API measures face and voice signals

Hume· 6 OctCapability change

Introducing Expression APIs: Give your AI more of what people mean

APIs that read tone, hesitation, and expression

hume.ai

· 29 Sep

Evaluating Google’s multi-speaker TTS: A case study in why private evaluations matter

Hume· 17 SepResearch paper

Introducing the Hume Voice Controllability Leaderboard

Leaderboard tests TTS model instruction following

Hume· 10 Sep

Introducing the Hume Voice Replication Leaderboard

New leaderboard ranks eleven text-to-speech models on voice replication quality.

Hume· 27 MayResearch paper

Disentangling Emotion from Voice: A Cross- Sampling Approach for Expressive Voice Data

Most covered

OpenAI OpenAI acquires Orchestra Bio
The Decoder: “OpenAI acquires Orchestra Bio to build AI agents that speed up drug development”
Reporting · 18 outlets
Image from openai.com
OpenAI· 20 Oct
OpenAI acquires Orchestra Bio
DeepSeek 🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
SCMP: “DeepSeek seeks ‘total victory’ over closed-source AI with new open-source tool”
Reporting · 14 outlets
DeepSeek· 20 Oct
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
OpenAI ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform
The Information: “OpenAI Expands ChatGPT Ads to 26 More Countries, Says It Has More Than 100,000 Advertisers”
Reporting · 12 outlets
Image from openai.com
OpenAI· 21 Oct
ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform
Meta Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster
RuntimeWire: “Meta says Prometheus delivered 85% goodput while training Muse Wonder”
Reporting · 7 outlets
Image from engineering.fb.com
Meta· 19 Oct
Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster
Inception Diffusion at Scale: Introducing Mercury 3
The Decoder: “Inception's Mercury 3 diffusion model claims to beat GPT-6 Luna and Claude Haiku 5.5 at a fraction of the wait”
Reporting · 6 outlets
Image from inceptionlabs.ai
Inception· 19 Oct
Diffusion at Scale: Introducing Mercury 3