ishine's Projects
Code and generated sounds for "Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning", MLSP 2021
基于重采样,相位声码器及BP神经网络基音分类的变声器,数学,UI及信号处理算法基于PainterEngine开发
This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
An implementation of the combination of Soft-VC and VITS
Wav2Vec for speech recognition, classification, and audio classification
Contains code for our work on speech to singing conversion (ICASSP 2020)
:sound: spafe: Simplified Python Audio-Features Extraction
A cross-platform framework for developing spatial audio algorithms and software in C/C++
Spatial Audio Generation
Spatial Audio Python Package
Speech Parameter Estimation Using Differentiable Speech Synthesizer
speaker diarization by uis-rnn and speaker embedding by vgg-speaker-recognition
Speaker verification using ResnetSE (EER=0.0093) and ECAPA-TDNN
Official implementation of the paper "SPEAKER VGG CCT: Cross-corpus Speech Emotion Recognition with Speaker Embedding and Vision Transformers, 2022"
The code for the INTERSPEECH paper "Speaker Embedding Extraction with Phonetic Information"
target speaker extraction and verification for multi-talker speech
multi-scale time domain speaker extraction
Speaker spotting based on embedding
Tensorflow implementation of generalized end-to-end loss for speaker verification
Deep Discriminative Embeddings for Duration Robust Speaker Verification
Identification of speakers in novels
Speaker Verification (GE2E Loss)