# \#speech-recognition

**URL:** https://scanalyst.fourmilab.ch/tag/speech-recognition/2862.md

[Latest](https://scanalyst.fourmilab.ch/latest.md) · [Categories](https://scanalyst.fourmilab.ch/categories.md) · [Tags](https://scanalyst.fourmilab.ch/tags.md)

---

## [Decoding Speech from Brain Wave Recordings](https://scanalyst.fourmilab.ch/t/decoding-speech-from-brain-wave-recordings/3830)

<div class="topic-metadata">

**Author:** [@johnwalker](https://scanalyst.fourmilab.ch/u/johnwalker)\
**Replies:** 1\
**Last updated:** [6 October 2023 13:03 UTC](https://scanalyst.fourmilab.ch/t/decoding-speech-from-brain-wave-recordings/3830 "2023-10-06T13:03:32Z")

</div>

A paper published in Nature Machine Intelligence on 2023-10-05, “Decoding speech perception from non-invasive brain recordings” (full text at link) reports identifying, with 41% accuracy, speech perceived by individuals …

---

## [OpenAI Releases “Whisper”—Open Source Neural Net Speaker-Independent Speech Recognition](https://scanalyst.fourmilab.ch/t/openai-releases-whisper-open-source-neural-net-speaker-independent-speech-recognition/2051)

<div class="topic-metadata">

**Author:** [@johnwalker](https://scanalyst.fourmilab.ch/u/johnwalker)\
**Replies:** 1\
**Last updated:** [23 September 2022 14:30 UTC](https://scanalyst.fourmilab.ch/t/openai-releases-whisper-open-source-neural-net-speaker-independent-speech-recognition/2051 "2022-09-23T14:30:19Z")

</div>

OpenAI has just released, under the MIT open source license, a speaker-independent speech recognition system called Whisper, which they say “approaches human level robustness and accuracy on English speech recognition”: …