603 views
# Linux Voice Interface There are several areas. ## Speech recognition (STT) Computer recognizes spoken words. Can be used to dictate texts. ### Projects - [OpenAI Whisper](https://openai.com/research/whisper) - [Coqui STT](https://github.com/coqui-ai/STT) (Fork of [Mozilla DeepSpeech](https://github.com/mozilla/DeepSpeech)) - [Facebook Wav2Letter++](https://github.com/flashlight/wav2letter/wiki) - https://github.com/Elleo/gst-deepspeech - https://github.com/Elleo/ibus-deepspeech ## Voice dataset Training deep-learning networks for speech recognition takes a lot of data. We need open datasets to build open technology. ### Projects - [Mozilla Common Voice Dataset](https://commonvoice.mozilla.org/en/datasets) - [Lingua Libre](https://lingualibre.org/wiki/LinguaLibre:Main_Page) - [Mycroft Open Dataset](https://mycroft.ai/blog/privacy-machine-learning-open-data-set-opt-feature/) - [Google Speech Commands Dataset](https://ai.googleblog.com/2017/08/launching-speech-commands-dataset.html) - [Google GigaSpeech](https://github.com/SpeechColab/GigaSpeech) - [LibriSpeech](https://www.openslr.org/12) - [TED-LIUM](https://www.openslr.org/51/) - [VoxForge](http://www.repository.voxforge1.org/downloads/SpeechCorpus/Trunk/) - [Tatoeba](https://tatoeba.org/eng/downloads) ## Voice control Control programs with the voice instead of mouse and keyboard. ## Voice assistant The computer can solve tasks that are input by voice and answers by voice. You can call that a conversation interface. ### Projects - [Mycroft](https://mycroft.ai/) - https://en.wikipedia.org/wiki/Mycroft_(software) - [Rhasspy](https://rhasspy.readthedocs.io/en/latest/) - [Almond](https://almond.stanford.edu/) - https://flathub.org/apps/details/edu.stanford.Almond - https://community.almond.stanford.edu/t/new-release-almond-2-0/444 - https://github.com/home-assistant/addons/tree/master/almond ## Speech output (TTS) Computer can output text with a natural sounding voice. ### Projects - [Coqui TTS](https://github.com/coqui-ai/TTS) - [Speech Dispatcher](https://freebsoft.org/speechd) (Wiki de: https://de.wikipedia.org/wiki/Speech_Dispatcher) - [Orca (assistive technology)](http://projects.gnome.org/orca/) (Wiki: https://en.wikipedia.org/wiki/Orca_(assistive_technology)) ## References - https://en.wikipedia.org/wiki/Speech_recognition_software_for_Linux - https://www.ubuntupit.com/best-open-source-speech-recognition-tools-for-linux/ - http://linux-sound.org/speech.html - https://makezine.com/2020/03/17/private-by-design-free-and-private-voice-assistants/ - https://www.linuxsecrets.com/archlinux-wiki/wiki.archlinux.org/index.php/Text_to_speech.html