GitHub

DePasqualeOrg/mlx-audio-plus

The best audio processing library built on Apple's MLX framework, providing fast and efficient text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS) on Apple Silicon. Kokoro Fast, ...
IEEE

A Bayesian Hybrid Attention Module for Underwater Acoustic Target Recognition

Abstract: The attention mechanism improves underwater acoustic target recognition (UATR) by suppressing irrelevant features. However, due to the uncertainty and scarcity of underwater acoustic target ...
IEEE

Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module

Abstract: The information loss or distortion caused by single-channel speech enhancement (SE) harms the performance of automatic speech recognition (ASR). Observation addition (OA) is an effective ...
GitHub

PEAK AI Virtual Assistant

PEAK is a desktop-style voice assistant with a web UI, built with Python and JavaScript. It uses speech recognition, text-to-speech, and an AI chatbot backend to handle natural-language commands, open ...