ishine's Projects
medical chatbot
Medical-domain Dialogue System for Diseases Identification
Computes the Mel-Cepstral Distance of two WAV files based on the paper "Mel-Cepstral Distance Measure for Objective Speech Quality Assessment" by Robert F. Kubichek.
基于involution的melgan,更加快速的音频合成方法
"Joint Detection and Classification of Singing Voice Melody Using Convolutional Recurrent Neural Networks"
c++ code for merlin tts
MESSL wrappers etc for JSALT 2015, including CHiME3
Official repository of https://arxiv.org/abs/2111.04040v1
Control adaptive filters with neural networks
metadv
MFixedPoint is a header-only fixed-point C++ library suitable for fast arithmetic operations on systems which don't have a FPU (e.g. embedded systems).. Suitable for performing computationally intensive operations on a computing platform that does not have a floating-point unit (like most smaller embedded systems, such as Cortex-M3, CortexM0, ATmega, PSoC 5, PSoC 5 LP, PSoC 4, Arduino platforms e.t.c). Common applications include BLDC motor control and image processing. Best performance on a 32-bit or higher architecture (although 8-bit architectures should still be fine).
We design a spectral compression mapping (SCM) for full-band speech enhancement, and propose a two-stage stream named MHA-DPCRN
Efficient neural networks for analog audio effect modeling
Tiny immediate-mode UI library
中文自然语言处理工具包
Milvus -- the world's fastest vector search engine.
A Pure Inference-Oriented framework implemented in C.
XiaoMi Natural Language Processing Toolkits
:telescope: Speaker diarization via transfer learning
MIPP is a portable wrapper for SIMD instructions written in C++11. It supports NEON, SSE, AVX and AVX-512.
Unsupervised WaveNet-based Singing Voice Conversion Using Pitch Augmentation and Two-phase Approach
Unofficial Multi-microphone complex spectral mapping for utterance-wise and continuous speech separation(MISO-BF-MISO)
The Medical Imaging Interaction Toolkit.