Conch
=====
[![Build Status](https://travis-ci.org/mmcauliffe/Conch-sounds.svg?branch=master)](https://travis-ci.org/mmcauliffe/Conch-sounds)
[![Coverage Status](https://coveralls.io/repos/github/mmcauliffe/Conch-sounds/badge.svg?branch=master)](https://coveralls.io/github/mmcauliffe/Conch-sounds?branch=master)
[![Documentation Status](https://readthedocs.org/projects/conch-sounds/badge/?version=latest)](http://conch-sounds.readthedocs.io/en/latest/?badge=latest)
[![PyPI version](https://badge.fury.io/py/conch_sounds.svg)](https://badge.fury.io/py/conch_sounds)
[![DOI](https://zenodo.org/badge/9966944.svg)](https://zenodo.org/badge/latestdoi/9966944)
This package contains functions for converting wav files into auditory
representations and calculating distance between them.
Auditory representations currently supported are mel-frequency cepstrum
coefficients (MFCCs) and amplitude envelopes.
Distance metrics currently implemented are dynamic time warping and
cross-correlation.
Installation
==================
The latest released version can be installed via:
`pip install conch_sounds`
Higher level wrappers
==================
In `conch/main.py` there are several wrapper functions for convenience.
Each of these functions takes keyword arguments corresponding to how auditory
representations should be constructed and what distance function to use.
**acoustic_similarity_mapping** takes a mapping of paths as its argument.
This argument should be a list of pairs or triplets of fully specified file names.
Pairs will compute the distance between the two files, and triplets will compute
an AXB style design, where distances are computed between the first element and the second and
between the third element and the second. In this case, the numerical output
will be a ratio of the third element's distance to the second divided by the
first element's distance to the second. The return value is a dictionary
with the pairs/triplets as keys, and the numerical output as the values.
**acoustic_similarity_directories** takes two arguments which are fully specified paths
to two directories. It then constructs a path mapping of all the files in
the first directory to all the files in the second directory. The return
value is a single value, which the average distance of all those calculated.
**analyze_directory** takes a single directory as an argument and creates a
path mapping of all the files compared to all other files. The return value is a dictionary
with the file pairs as keys, and the numerical output as the values.
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
conch-sounds-0.2.4.tar.gz (53个子文件)
conch-sounds-0.2.4
PKG-INFO 682B
conch
distance
dct.py 1KB
dtw.py 3KB
__init__.py 186B
point.py 1KB
xcorr.py 1KB
base.py 1KB
main.py 6KB
multiprocessing.py 11KB
utils.py 1KB
io.py 487B
__init__.py 319B
analysis
formants
formant_track_segment.praat 1KB
formant_track.praat 912B
praat.py 2KB
lpc.py 8KB
formant_point_segment.praat 1KB
__init__.py 189B
formant_point.praat 1KB
helper.py 6KB
functions.py 4KB
mfcc
praat.py 600B
rastamat.py 4KB
mfcc.praat 1KB
__init__.py 74B
intensity
intensity_track_segment.praat 911B
praat.py 832B
intensity_track.praat 496B
__init__.py 84B
praat.py 467B
pitch
pitch_track_with_pulses.praat 958B
praat.py 3KB
pitch_track_segment.praat 1KB
reaper.py 3KB
__init__.py 175B
pitch_track_with_pulses_segment.praat 1KB
pitch_track.praat 727B
autocorrelation.py 6KB
amplitude_envelopes
amplitude_envelopes.py 3KB
__init__.py 60B
gammatone.py 1KB
segments.py 4KB
specgram.py 1KB
__init__.py 216B
exceptions.py 1KB
conch_sounds.egg-info
PKG-INFO 682B
requires.txt 54B
SOURCES.txt 2KB
top_level.txt 6B
dependency_links.txt 1B
setup.cfg 108B
setup.py 2KB
README.md 3KB
共 53 条
- 1
资源评论
挣扎的蓝藻
- 粉丝: 13w+
- 资源: 15万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功