Search Results for "speaker identification"

Speech-to-text, text-to-speech, and speaker recognition using next-gen Kaldi with onnxruntime without an Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift, Dart, JavaScript, Flutter.

..., reconfigurable vocabulary and speaker identification. Speech recognition bindings are implemented for various programming languages like Python, Java, Node.JS, C#, C++, Rust, Go and others. Vosk supplies speech recognition for chatbots, smart home appliances, and virtual assistants. It can also create subtitles for movies, and transcription for lectures and interviews. Vosk scales from small devices like Raspberry Pi or Android smartphones to big clusters.

This library implement RIMS controls for home brewers. For definition of a RIMS, see https://tinyurl.com/j3lyuyc For me, an Arduino micro controller + a LCD Keypad shield was cheaper and a lot more customizable than a commercial PID controller. So, with this library, a commercial PID controller is unnecessary. Automatic PID tuning toolkit is also included. Temperature can be read with a thermistor, a resistance temperature detector (RTD) or any custom temperature probe. Heater is...

SharpEar is a "Microphone array" simulation project. Its simulates a "Microphone Array" and "Room". User can add voice, noice, moving voices in to the Room. After User selects a .wav file and a position for this sound in the room; user can trigger beamforming . According to the position of the "Microphone Array" and "Sound Sources" beamforming will color the room. User can choose a "Sound" as "Noice", "Voice" or even a Moving "Voice".

Speaker Finder is speaker identification tool powered by 3 different technique in the background . 1 - GMM with GFCC (gammatone filter ceptral coefficient) 2 - GMM with Pitch(f0) 3 - NGrams with f0 SpeakerFinder should be trained with speaker's sound first than, program can be used the recognized trained speakers. Project also has a validation phase which choose which algorithm above 3 will give best result for spesific speaker.