speech_feature_extractor
所属分类：其他
开发工具：Python
文件大小：40KB
下载次数：0
上传日期：2020-10-06 13:04:46
上 传 者：
jyh351
说明： 语音增强算法中训练特征生成；训练目标的生成；
(Training feature generation in speech enhancement algorithm; Generation of training objectives;)
文件列表:
speech_feature_extractor\ams_extractor.py (3196, 2018-05-27)
speech_feature_extractor\cal_pitch_based_feature.py (1086, 2019-10-21)
speech_feature_extractor\cal_triangle_window.py (1572, 2019-10-21)
speech_feature_extractor\cochleagram_extractor.py (8754, 2018-05-27)
speech_feature_extractor\feature_extractor.py (21389, 2019-10-21)
speech_feature_extractor\gfcc_extractor.py (924, 2018-05-27)
speech_feature_extractor\mfcc_extractor.py (4293, 2018-05-27)
speech_feature_extractor\piliangjiangcaiyanglv.sh (102, 2020-01-09)
speech_feature_extractor\rasta_plp_extractor.py (4352, 2018-05-27)
speech_feature_extractor\read_sphere_wav.py (1105, 2019-10-21)
speech_feature_extractor\spectrum_extractor.py (1421, 2019-10-21)
speech_feature_extractor\speech_mixer.py (2289, 2019-10-22)
speech_feature_extractor\speech_synthesis.py (2877, 2019-11-07)
speech_feature_extractor\speech_utils.py (24386, 2019-11-07)
speech_feature_extractor\__pycache__\feature_extractor.cpython-37.pyc (18293, 2019-11-07)
speech_feature_extractor\__pycache__\read_sphere_wav.cpython-37.pyc (1107, 2019-11-07)
speech_feature_extractor\__pycache__\speech_mixer.cpython-37.pyc (1722, 2019-11-07)
speech_feature_extractor\__pycache__\speech_utils.cpython-37.pyc (17240, 2019-11-07)
speech_feature_extractor\__pycache__ (0, 2020-01-19)
speech_feature_extractor (0, 2020-06-23)
# 2018-05-27 Update Feature Extractors and Utils
All implemented feature extractors have been written in the file ‘feature_extractor.py’. Please use this file for the newest
version.
所有实现的特征提取器都写在文件“feature_extractor.py”中。请使用此文件的最新版本。
# Speech Feature Extractors
1. Features include: MFCC, GFCC, gammatone filterbank, Power Spectrum, Log-Power Spectrum, Amplitude Modulation Spectrum(AMS, two version), Short-Time-Fourier-Transfer Spectrum.
2. Utils include: Ideal Binary Mask, Ideal Ratio Mask, Speech synthesis method, Mixer by dB
3. Normalizer include: zero-to-one normalizer, unit-vector normalizer.
语音特征提取器
1. 特点包括:MFCC, GFCC, gammatone滤波器组,功率谱,对数功率谱,调幅谱(AMS,两个版本),短时傅立叶转移谱。
2. 主要包括:理想二进制掩码、理想比例掩码、语音合成方法、dB混频器
3.归一化器包括:0到1归一化器,单位向量归一化器
近期下载者：
相关文件：
收藏者：