Hume

Last 4 weeks · 1 post · 0 outlets writing · no. 30 of 33 by coverage

Hume has made 1 first-party announcement in the last 4 weeks. Latest: Measuring benchmark optimization in speech recognition, 21 August 2026.

Window4w8w 12w 26w

Announcements and coverage, week by week

17–23 Aug→ 7–13 Sep…

17–23 Aug24–30 Aug31 Aug–6 Sep7–13 Sep…

Postspeak 1/wk

Coveragepeak 1/wk

Hume — forck.live

← Feed RSS

Hume

@hume_ai

Last 4 weeks · 1 post · 0 outlets writing · no. 30 of 33 by coverage

Hume has made 1 first-party announcement in the last 4 weeks. Latest: Measuring benchmark optimization in speech recognition, 21 August 2026.

Window4w8w 12w 26w

Announcements and coverage, week by week

17–23 Aug→ 7–13 Sep…

17–23 Aug24–30 Aug31 Aug–6 Sep7–13 Sep…

Postspeak 1/wk

Coveragepeak 1/wk

Who covers them

No outlet coverage resolved inside this window.

Posts2 Coverage

HumeResearch paper· 17 days ago

Measuring benchmark optimization in speech recognition

Hume introduced three tests to quantify benchmark optimization in speech recognition. The research found that top open-source ASR models reproduce benchmark transcripts even when the audio…

HumeResearch paper· 27 May

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

Hume presents a cross-product sampling approach for disentangling emotion from voice in expressive voice data.