GitHub

Nhantran65/drone_audio_detection

This repository is a proof of concept for detecting drone audio in short window-level recordings. The current POC includes product contracts, manifest validation, professor data audit tooling, public ...
note

20 Hermes Agent Creative Skills: From Diagrams to Music

The third installment of this series covers the largest category in Hermes Agent: "Creative & Media". This covers 20 skills in total: 16 creative skills and 4 media skills. It includes everything ...
GitHub

Speech-to-Text-WaveNet: End-to-end sentence level English speech recognition

A tensorflow implementation of speech recognition based on DeepMind's WaveNet: A Generative Model for Raw Audio. (Hereafter the Paper) Although ibab and tomlepaine have already implemented WaveNet ...
Frontiers

Multi-QuadEmoNet: cat and dog emotion classification model from animal vocalization using multi-stage LSTM-GRU paradigm

This robust MFCC extraction process captures essential vocal characteristics, allowing our models to discern emotional nuances in the audio data. The efficiency of MFCC in representing emotional ...
Frontiers

Data-driven refinements for voice disorder classification: improving accuracy and generalisability

Scalable Methods and Emerging Technologies to Advance Clinical Implementation of Vocal Biomarkers ...
IEEE

Emerging Technologies and Applications (MPSec ICETA), IEEE International Conference on

Modern manufacturing processes depend heavily on industrial robots with vision systems installed, which allow them to perform tasks like tracking, manipulation, and object recognition. But one major ...