該資源是在GitHub上ID為【mxer】的小夥伴分享的語音方向的資源,以下為原地址:https://github.com/mxer/awesome-speech#1.2
以下為目錄,如果喜歡,可以複製連結進行跳轉:
1.page
Xingyu Na
LanguageProcessing and Pattern Recognition in University of Aachen
Fernando de laCalle Silos
2.open source library/toolbox/code
HTK
Py2HTK
parallel-htk
HTK_C_MATLAB_tools
Kaldi:
Kaldi官方文檔(中文版)
Kaldi models
Corpus PhoneticsTutorial
py-kaldi-asr
https://github.com/pykaldi/pykaldi
https://github.com/gooofy/py-kaldi-asr
https://github.com/UFAL-DSG/pykaldi
https://github.com/janchorowski/kaldi-python
Dan's DNNimplementation:
pytorch-kaldi
kaldi-lstm
kaldi-ctc
keras-kaldi
python wrapperfor kaldi-online-decoder
Kaldi+PDNN
tfkaldi
Kaldi_CNTK_AMI
kaldi-io-for-python
kaldi-pyio
kaldi-tree-conv
kaldi-ivector
kaldi-yesno-tutorial
Kaldi nnet3 教程
Josh Meyer'sWebsite
Adapting your ownLanguage Model for Kaldi
Some Kaldi Notes
http://jrmeyer.github.io/asr/2016/02/01/Kaldi-notes.html
http://sentiment-mining.blogspot.com/
http://pages.jh.edu/~echodro1/tutorial/kaldi/
kaldi_tutorial
Online decoderfor Kaldi NNET2 and GMM speech recognition models with Pythonbindings
ResNet-Kaldi-Tensorflow-ASR
Kaldi ASR:Extending the ASpIRE model
FastCGI supportfor Kaldi ASR
alignUsingKaldi
kaldi-readers-for-tensorflow
kaldi-iot
lattice-info
lattice-char-to-word
lattice-word-length-distribution
kaldi-lattice-word-index
kaldi-decoders
lattice-remove-ctc-blank
kaldi-lattice-search
htk2kaldi
parallel-kaldi
kaldi在線中文識別系統搭建
kaldi-docker
CSLT-Sparse-DNN-Toolkit
featxtra
Sphinx
https://cmusphinx.github.io/
https://github.com/cmusphinx
https://github.com/cmusphinx/pocketsphinx
OpenFst
http://www.openfst.org/twiki/bin/view/FST/WebHome
https://github.com/UFAL-DSG/openfst
https://github.com/benob/openfst-utils
https://github.com/vchahun/pyfst
MIT SpokenLanguage Systems
Julius
Bavieca
Simon
SIDEKIT
SRILM
https://www.sri.com/engage/products-solutions/sri-language-modeling-toolkit
http://www.speech.sri.com/projects/srilm/
https://github.com/nuance1979/srilm-python
https://github.com/njsmith/pysrilm
awd-lstm-lm
ISIP
MIT Finite-StateTransducer (FST) Toolkit
MIT LanguageModeling (MITLM) Toolkit
OpenGrm
RNNLM
http://www.fit.vutbr.cz/~imikolov/rnnlm/
https://github.com/IntelLabs/rnnlm
https://github.com/glecorve/rnnlm2wfst
faster-rnnlm
CUED-RNNLMToolkit
Using RNNLMrescoring a sentence in Chinese ASR system
KenLM
rwthlm
word-rnn-tensorflow
tensorlm
SpeechRecognition
SpeechPy
Aalto
google-cloud-speech
apiai
https://pypi.org/project/apiai/
wit
Nabu
asr-study
dejavu
uSpeech
Juicer
PMLS
dragonfly
SPTK
https://github.com/r9y9/SPTK
https://github.com/sp-nitech/SPTK
http://sp-tk.sourceforge.net/
pysptk
RWTH ASR
Palaver
Praat
SpeechRecognition Grammar Specification
Automatic_Speech_Recognition
speech-to-text-wavenet
tensorflow-speech-recognition
tensorflow_end2end_speech_recognition
tensorflow_speech_recognition_demo
AVSR-Deep-Speech
TTS and ASR
CTC + TensorflowExample for ASR
tensorflow-ctc-speech-recognition
speechT
end2endASR
NADU
DTW (Dynamic TimeWarping) python module
Various scriptsand tools for speech recognition model building
基於深度學習的語音識別系統,使用CNN、LSTM和CTC實現的中文語音識別系統
tacotron_asr
ASR_Keras
Kaggle TensorflowSpeech Recognition Challenge
Speechrecognition script for Asterisk that uses google's speech engine
Libraries andscripts for manipulating and handling ASR output/n-bests/etc
Some scripts andcommands for working with ASR
PySpeechGrammar
Python module forevaluating ASR hypotheses
edit-distance
3.dataset
VoxForge
http://www.voxforge.org/home
http://www.voxforge.org/zh
http://www.repository.voxforge1.org/downloads/SpeechCorpus/Trunk/Audio/Main/16kHz_16bit/
ASR Audio DataLinks
The CMUPronouncing Dictionary
TIMIT
https://catalog.ldc.upenn.edu/LDC93S1
https://github.com/syhw/timit_tools
https://github.com/philipperemy/timit
GlobalPhoneLanguage Models
1 Billion WordLanguage Model Benchmark
DaCiDian-Develop
AISHELL
CC-CEDICT
https://www.mdbg.net/chinese/dictionary?page=cc-cedict
TED-LIUM
open-asr-lexicon
4.Tutorial
University ofEdinburgh ASR2017-18
stanford CS224s
NYU asr12
SpeechRecognition with Neural Networks
page
CSTR-Edinburgh
open source library/toolbox
WORLD
HTS
http://hts.sp.nitech.ac.jp/
http://hts-engine.sourceforge.net/
https://github.com/shamidreza/HTS-demo_CMU-ARCTIC-SLT-Formant
https://github.com/MattShannon/HTS-demo_CMU-ARCTIC-SLT-STRAIGHT-AR-decision-tree
Tacotron
https://github.com/Kyubyong/tacotron
https://github.com/Kyubyong/expressive_tacotron
https://github.com/keithito/tacotron
https://github.com/GSByeon/multi-speaker-tacotron-tensorflow
https://github.com/r9y9/tacotron_pytorch
https://github.com/soobinseo/Tacotron-pytorch
Tacotron2
https://github.com/NVIDIA/tacotron2
https://github.com/riverphoenix/tacotron2
https://github.com/A-Jacobson/tacotron2
https://github.com/selap91/Tacotron2
https://github.com/LGizkde/Tacotron2_Tao_Shujie
https://github.com/rlawns1016/Tacotron2
https://github.com/CapstoneInha/Tacotron2-rehearsal
Merlin
mozilla TTS
Flite
Speect
Festival
eSpeak
nnmnkwii
Ossian
gTTS
gnuspeech
supercollider
sc3-plugins
Neural_Network_Voices
pggan-pytorch
cainteoir-engine
loop
nnmnkwii
TTS and ASR
musa_tts
marytts(JAVA)
1.open source library/toolbox
Alize
speaker-recognition-py3
openVP
2.Genderrecognition by voice and speech analysis
page
NTU
Tsung-Hsien Wen
open source library/toolbox
PyDial
alex
ROS 語音交互系統
結合ROS框架的中文語音交互系統
1.Speech Processing
madmom
pydub
kapre: KerasAudio Preprocessors
BTK
EspNet
Signal-Processing
pyroomacoustics
librosa
REAPER
MSD_split_for_tagging
VOICEBOX
liquid-dsp
ffts
mir_eval
aupyom
Pitch Detection
TFTB
maracas
SRMRpy
ssp
iss
asr_preprocessing
asrt
Audio superresolution using NN
RNN training fornoise reduction in robust asr
RNN for audionoise reduction
muda
Efficient samplerate conversion in python
Smarc audio rateconverter
Python scripts tocomputes f0s of a wave file
2.Audio I/O
PortAudio
audiolab
pytorch audio
Digital SpeechDecoder
audioread
audacity.py
3.Sound Source Separation
HARK
Deep RNN forSource Separation
nussl
DNN for MusicSource Separation in Tensorflow
Alexey Ozerov
University ofSurrey CVSSP
source separationusing CNN
4.FeatureExtraction
openSMILE
veles.sound_feature_extraction
vamp-plugin-sdk
Yaafe
py_bank
AuditoryFilterbanks
python_speech_features
VAD
https://github.com/jtkim-kaist/VAD
https://github.com/jtkim-kaist/VAD_DNN
https://github.com/marsbroshok/VAD-python
https://github.com/shiweixingcn/vad
https://github.com/fedden/RenderMan
rVAD
Aurora 2 VAD
IsraelCohen
Python interfaceto the WebRTC Voice Activity Detector
1.code/tool/data
cmusphinx
julius-speech
OpenSLR
List of speechrecognition software
KTH
VERBIO
timeview
Speech at CMU WebPage
CMU Robust SpeechGroup
Speech Softwareat CMU
Aalto SpeechResearch
CMU FestvoxProject
CSTR
Xiph
Brno Universityof Technology Speech Processing Group
SoX
STRAIGHT
Idiap ResearchInstitute
Transcriber
Amirsina Torfi
The SpeechRecognition Virtual Kitchen
SparseRepresentation & Dictionary Learning Algorithms with Applicationsin Denoising, Separation, Localisation and Tracking
Audacity
beetbox
CAQE
UCL Speech FilingSystem
Ryuichi Yamamoto
Kyubyong Park
HideyukiTachibana
Colin Raffel
Paul Dixon
smacpy
c4dm
Matt Shannon
Keunwoo Choi
ADASP
uchicago Speechand Language @ TTIC
justin salamon
COLEA
openAUDIO
Praat
librosa
Essentia
timmahrt
Lefteris Zafiris
audio-to-audioand audio-to-midi alignment
DNN based hotwordand wake word detection toolkit
free-spoken-digit-dataset
中文語言資源聯盟
Institute ofFormal and Applied Linguistics – Dialogue Systems Group
https://github.com/UFAL-DSG
https://github.com/edobashira/speech-language-processing
https://github.com/andabi?tab=repositories
https://code.soundsoftware.ac.uk/projects
2.tutorial
DL for ComputerVision, Speech, and Language
臺大數位語音處理概論
IISc SpeechInformation Processing
paper
https://arxiv.org/search/?query=speech&searchtype=all&source=header
https://www.isca-speech.org/iscaweb/index.php/archive/online-archive
https://www.aclweb.org/anthology/
https://github.com/zzw922cn/awesome-speech-recognition-speech-synthesis-papers
states of thearts and recent results (bibliography) on speech recognition
Dan Povey
cmusphinx
CMU LanguageTechnologies Institute
CMU SPEECH@SV
MitsubishiElectric Research Laboratorie
MIT SpokenLanguage Systems
Brno Universityof Technology Speech Processing Group
IISc
uchicago Speechand Language @ TTIC
RWTH AachenUniversity
TOKUDA andNANKAKU LABORATORY
Institute ofFormal and Applied Linguistics – Dialogue Systems Group
Ohio StateUniversity speech separation
LEAP Laboratory
Hainan Xu
Mark Gales
Karen Livescu
Shubham Toshniwal
Adrien Ycart
Ron Weiss
Yajie Miao
Scott T Wisdom
Alan W Black
Amirsina Torfi
Liang Lu
Zhizheng WU
justin salamon
Karen Livescu
Shubham Toshniwal
Keith Vertanen
Aviv Gabbay
Mehryar Mohri
Jonathan LE ROUX
Suyoun Kim
DeepSound
Lei Xie
該資源是在GitHub上ID為【msgi】的小夥伴分享的NLP相關的資源,以下為原地址:https://github.com/msgi/nlp-journey
以下為目錄,如果喜歡,可以複製連結進行跳轉:
https://github.com/msgi/nlp-journey/blob/master/docs/tools.md
https://github.com/msgi/nlp-journey/blob/master/docs/alg.md
https://github.com/msgi/nlp-journey/blob/master/docs/basic.md
https://github.com/msgi/nlp-journey/blob/master/docs/fq.md
https://github.com/msgi/nlp-journey/blob/master/docs/notes.md
https://pan.baidu.com/share/init?surl=sE_20nHCfej6f9yRaisz7Q
http://www.ituring.com.cn/book/1605
https://www.deeplearningbook.org/
http://neuralnetworksanddeeplearning.com/
https://nndl.github.io/
http://web.stanford.edu/~jurafsky/slp3/ed3book.pdf
http://cs224d.stanford.edu/
1.算法模型與優化
http://www.bioinf.jku.at/publications/older/2604.pdf
https://arxiv.org/pdf/1207.0580.pdf
https://arxiv.org/pdf/1512.03385.pdf
https://arxiv.org/pdf/1502.03167.pdf
2.綜述論文
https://arxiv.org/pdf/1812.08951.pdf
https://arxiv.org/pdf/1803.07133.pdf
3.語言模型
https://www.researchgate.net/publication/221618573_A_Neural_Probabilistic_Language_Model
https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf
4.文本增強
https://arxiv.org/pdf/1901.11196.pdf
5.文本預訓練
https://arxiv.org/pdf/1301.3781.pdf
https://arxiv.org/pdf/1405.4053.pdf
地址https://arxiv.org/pdf/1607.04606.pdf
解讀https://www.sohu.com/a/114464910_465975
https://nlp.stanford.edu/projects/glove/
https://arxiv.org/pdf/1802.05365.pdf
https://arxiv.org/pdf/1810.04805.pdf
https://arxiv.org/pdf/1906.08101.pdf
https://arxiv.org/pdf/1906.08237.pdf
6.文本分類
https://arxiv.org/pdf/1510.03820.pdf
https://arxiv.org/pdf/1408.5882.pdf
https://www.aclweb.org/anthology/P16-2034
7.文本生成
https://arxiv.org/pdf/1805.06553.pdf
https://arxiv.org/pdf/1609.05473.pdf
https://arxiv.org/pdf/1605.05396.pdf
8.文本相似性
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.723.6492&rep=rep1&type=pdf
https://www.aclweb.org/anthology/W16-1617
9.短文本匹配
http://papers.nips.cc/paper/5019-a-deep-architecture-for-matching-short-texts.pdf
10.自動問答
https://arxiv.org/pdf/1801.08290.pdf
https://arxiv.org/pdf/1812.08989.pdf
https://arxiv.org/pdf/1702.01932.pdf
https://arxiv.org/pdf/1512.01337v1.pdf
https://arxiv.org/abs/1612.01627
https://arxiv.org/pdf/1806.09102.pdf
https://www.aclweb.org/anthology/P18-1103
11.機器翻譯
https://arxiv.org/pdf/1406.1078v3.pdf
https://arxiv.org/pdf/1706.03762.pdf
https://arxiv.org/pdf/1901.02860.pdf
12.自動摘要
https://arxiv.org/pdf/1704.04368.pdf
13.事件提取
https://pdfs.semanticscholar.org/ca70/480f908ec60438e91a914c1075b9954e7834.pdf
14.推薦系統
https://arxiv.org/pdf/1905.06874.pdf
必讀博文
https://jalammar.github.io/illustrated-transformer/
http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp/
https://www.countbayesie.com/blog/2017/5/9/kullback-leibler-divergence-explained
https://blog.keras.io/building-autoencoders-in-keras.html
https://nlpoverview.com/
https://github.com/msgi/nlp-journey
https://www.cnblogs.com/rucwxb/p/10277217.html
https://zhuanlan.zhihu.com/p/49271699
https://zhuanlan.zhihu.com/p/70257427
https://mp.weixin.qq.com/s?__biz=MzI4MDYzNzg4Mw==&mid=2247488287&idx=2&sn=aa7b045337940886d5a7767f95ab0128&chksm=ebb42bcbdcc3a2ddcfb73fb77bead9655d6608b1a951a8b429fb2c38d56ca92289e97e6decd1&mpshare=1&scene=24&srcid=0930GzGGm3m7uZfJyblgWV3k&key=5b1b221b044835abb8ce952ed69e6acdfe5f30700caa3c560c8fe663354916c6753858e4dbbf1b4d1c2eded3876c67c0983d3d51324c321458405b0cacec9103640c28a7a5c068729172703bf23c0348&ascene=14&uin=Mjk3NzQ2NDczMQ%3D%3D&devicetype=Windows+10&version=62060833&lang=zh_CN&pass_ticket=uQSzwn38HjOIK%2BZwFf5AXCp%2Fk0QiE7budc%2Bl5t1yBFtOXA%2BPvSaFwqUWEwEmyZEd
https://github.com/msgi/nlp-journey/tree/master/nlp/embedding
fasttext(skipgram+cbow)
gensim(word2vec)
https://github.com/msgi/nlp-journey/blob/master/nlp/similaritybilstm+crf
https://github.com/CyberZHG/keras-gpt-2
https://github.com/jiangxinyang227/textClassifier
https://github.com/Lsdefine/attention-is-all-you-need-keras
https://github.com/miroozyx/BERT_with_keras
https://github.com/CyberZHG/keras-bert
https://github.com/iliaschalkidis/ELMo-keras
https://github.com/tyo-yo/SeqGAN
http://www.52nlp.cn/
https://kexue.fm/category/Big-Data
https://www.cnblogs.com/pinard/
https://tobiaslee.top/
https://github.com/msgi/nlp-journey
https://www.jiqizhixin.com/
https://colah.github.io/
https://zhpmatrix.github.io/
http://www.wildml.com/
http://www.shuang0420.com/
https://www.zybuluo.com/hanbingtao/note/433855
https://www.aclweb.org/portal/
https://www.emnlp-ijcnlp2019.org/
https://www.sheffield.ac.uk/dcs/research/groups/nlp/iccl/index#tab00
https://nips.cc/
https://www.aaai.org/
https://www.ijcai.org/
https://icml.cc/