Skip to content
View recklight's full-sized avatar
2 followers · 1 following
  • Taiwan

Highlights

  • Pro

Block or report recklight

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
recklight/README.md

typing

followers   stars   kudio downloads

~/recklight $ cat profile.py

class RL:
    role      = "Acoustic & Speech Signal Processing Researcher"
    location  = "Taiwan (UTC+8)"
    focus     = ["speech enhancement", "acoustic anomaly detection",
                 "feature extraction (STFT / MFCC)", "microphone arrays & DOA"]
    deploy_on = ["NVIDIA Jetson (Xavier AGX / NX)", "Raspberry Pi", "Linux clusters"]
    now       = "training speech-enhancement nets · building acoustic inspection tools"
    motto     = "Every signal has a story — filter the noise, keep the meaning."

⚙️ Signal Chain · Tech Stack

  [ Mic / Array ] ──► [ DSP Front-end ] ──► [ Features ] ──► [ Neural Model ] ──► [ Edge Deploy ]
     ReSpeaker          STFT · VAD · NS       MFCC · Δ          CNN · DAE           Jetson · RPi


📡 Featured Projects

🎛️ Kudio
Lightweight, composable audio toolkit for acoustic inspection — I/O, features, augmentation, enhancement & quality metrics.

🔊 SpeechDsp
Pure NumPy/SciPy speech front-end: framing, STFT, MFCC, VAD, enhancement and imbalance-aware metrics.

🎙️ micring
Cross-platform CLI for the ReSpeaker 4-Mic Array — recording, DOA, VAD, DSP tuning, LED ring & spectrograms.

📶 SymLoc
Tamper-robust likelihoods for Wi-Fi fingerprint localization via elementary symmetric polynomials.

🧠 SaDAE
Speaker-Aware Deep Denoising Autoencoder for speech enhancement.

⚡ MyJetsonNote
Environment setup notes for NVIDIA Jetson (Xavier AGX / NX) edge inference.

View all repositories →

📈 Telemetry

GitHub stats Top languages

GitHub streak

📫 Reach me through GitHub · 📍 Taiwan

Pinned Loading

  1. MyJetsonNote MyJetsonNote Public

    Environment setup for Nvidia Jetson series -> Xavier AGX, Xavier NX. Nvidia邊緣裝置環境建置

    2

  2. SE-Basic SE-Basic Public

    Speech enhancement based on neural networks 基於神經網路的語音增強

    MATLAB 3

  3. SaDAE SaDAE Public

    Speaker-Aware Deep Denoising Autoencoder with Embedded Speaker Identity for Speech Enhancement

    MATLAB 1