popcornell/MicRank
MicRank is a Learning to Rank neural channel selection framework where a DNN is trained to rank microphone channels.
MicRank helps improve the accuracy of distant speech recognition systems by automatically identifying the most effective microphones in a multi-microphone setup. It takes audio streams from various microphones and outputs a ranked list, allowing you to select the best channels for processing. This tool is ideal for engineers and researchers developing voice assistants, meeting transcription systems, or other applications relying on robust speech detection from multiple audio sources.
No commits in the last 6 months.
Use this if you need to optimize speech recognition performance in environments with multiple, potentially unsynchronized microphones, where some channels might be noisy or distant from the speaker.
Not ideal if your application uses a single microphone or if you require sample-level synchronization between devices for other processing steps.
Stars
22
Forks
4
Language
Python
License
—
Category
Last pushed
Apr 08, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/popcornell/MicRank"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
julius-speech/julius
Open-Source Large Vocabulary Continuous Speech Recognition Engine
rolczynski/Automatic-Speech-Recognition
🎧 Automatic Speech Recognition: DeepSpeech & Seq2Seq (TensorFlow)
tabahi/formantfeatures
Extract frequency, power, width and dissonance of formants from wav files
libdriver/ld3320
LD3320 full-featured driver library for general-purpose MCU and Linux.
awsaf49/audio_classification_models
Tensorflow Audio Classification Models