AI_GC_Methodology_2018_v1(private)
大戰略
Data_Gitlab
MATTBN
cd1
Train_1
PTND20011107.name.trs
PTSND20011107.trs
license.md_MATTBN
NER-PhA-Vol1
Train_NER-PhA-Vol1
data_NER-PhA-Vol1
CS_創設市集
CS_20160218
CS_20160218_001.textgrid
CS_20160218_001.txt
CS_20160218_001.wav
CS_20160324
GJ_國際教育新動線
GJ_20160208
speaker_xlsx_file
LICENSE_NER-PHA-Vol1
NER-Trs-Vol1
NER-Auto-Vol1
PTS-MSub-Vol1
Taiwanese-Speech-in-the-wild
ReadMe.md_file_TSW
Neural Machine Translation (seq2seq)
train-build_NMT_system
Inference-generate_translations
Attention-based_NMT_model
Tips&Tricks
Benchmarks
Attention-based Model (李宏毅教授)
Attention-based Model (Prof. 李宏毅)
Attention-based Model (in RNN ML#21-2 Prof. 李宏毅)
Toward Machine Comprehension of Spoken Contents
TOFEL
Task_and_Contribution
Attention-based Multi-hop Recurrent Neural Network (AMRNN) framework
AMRNN_framework_v1
Experiment_AMRNN
Cosine_Similarity
bi-directional GRU
AI_GC_比賽
AI_GC_比賽策略
AI_GC_比賽策略_0320_0520 2018
AI_GC_比賽策略_0801_0915_2018
AI_GC_比賽消息
AI語音首支測試檔上線＿0608
AI語音首支測試檔_0608
又慶錄音部長錄音
科技大擂台與AI對話_正式賽_細部賽制_0524
教育廣播電臺與國立臺北科技大學合作_0424
Gitlab開放通知_0411
Kaggle1
目錄A_Kaggle1
附錄_Kaggle1
AI Grand Challenge 6/23 第一次初賽
導入python packages (6/23比賽)
Setup Google Speech-to-Text Service
get all choices *.wav files and initialize answer_per_Q
Load Audio Files and Sentence Segmentation
Inspect Audio Non-silence Intervals
Use Google Speech-to-Text API
Assign answer_per_Q
Save Answers to CSV file
Kaggle2
Speech Audio Band-pass Filter
ai小老師人工校正答案規劃
ai 小老師操作細節
anaconda install
kaggle2_answe_M 資料夾目錄
task.py
題目分組
如何使用 Google Cloud Speech-to-Text Service
開通免費試用Google雲端服務
Tutorial of Running Google Cloud Speech-to-Text Service on Local Computer
Transcription Example from official Github
Sentence Segmentation 規劃
Match audio
Filter and Slience Removal
split + noise removal
aS.silenceRemoval()
Appendix
ai小老師人工校正答案規劃架構2
Noise Reduction
Audacity
Human speech frequency band-pass filter
Google_Cloud_speect-to-text
How-to_Guildes_Google_Cloud
Transcribing_long_audio_file
QuickStarts_Google_Cloud_speech-to-text
QuickStart_using_client_libraries
Cloud Speech-to-Text Basics
第一版 手動切 + Google Cloud Speech-to-Text Service
嘗試 Running Google Cloud Speech-to-Text Service on Colab
Kaggle3
Sentence Segmentation
Google Speech-to-Text API Experiment
Approach 1: Post-Transcription Keyword based Segmentation
Appendix
Python Audio APIs
PyAudio
pyAudioAnalysis3
librosa
題目分組細節
團隊資料
Python Basic target on AI_GC
hidden function definition
Module, Package, Library
Colab
Running Python code in Colab
Load external data: Google Drive, Sheets, and Cloud Storage
Schematic of colab service and overall process
RNN-LSTM example using Colab service
reader_test.py_file
reader_test.py and reader.py
class PtbReaderTest
def setUp(self)
def testPtbRawData(self)
def testPtbProducer(self)
reader.py_file
from __future__ import absolute_import
def _read_words(filename)
def _build_vocab(filename)
def _file_to_word_ids(filename, word_to_id)
def ptb_raw_data(data_path=None)
def ptb_producer(raw_data, batch_size, num_steps, name=None)
ptb_word_lm.py_file
importing_module_RNN_LSTM_example
from __future__ import xxxx
相對匯入與絕對匯入
class PTBModel (object)
__init___RNN_LSTM_example
class __init__
tf.device() 指定運行設備
tf.get_variable 函數的使用
tf.nn.embedding_lookup ()
tf.nn.dropout ()
tf.nn.xw_plus_b()
tf.trainable_variables()
tf.train.GradientDescentOptimizer()
apply_gradients()
_build_rnn_graph_RNN_LSTM_example
_build_rnn_graph_cudnn_RNN_LSTM_example
_get_lstm_cell_RNN_LSTM_example
_build_rnn_graph_lstm_RNN_LSTM_example
assign_lr_RNN_LSTM_example
export_ops_RNN_LSTM_example
import_ops_RNN_LSTM_example
def main(_)
util.py_file
def export_state_tuple(state_tuples, name) and def import_state_tuples(state_tuples, name, num_replicas)
def with_prefix(prefix, name) and def with_autoparallel_prefix(replica_id, name)
class UpdateCollection(object)
def __init__(self, meta graph, model)
def update_snapshot_name(self, var_coll_name)
def replicate_states(self, state_coll_name)
def auto_parallel(meta graph, model)
__init__.py_file
__init__.py file 的用途
Appendix 附錄
tf.flags
Tutorial_Web_RNN_tensorflow
GitHub_RNN-LSTM_example
Official_models_Tensorflow
Tensorflow_Research_Models
Samples_in_Tensorflow_Model
Vector_Representation_of_words_Tensorflow_Tutorial
VRW_Tensorflow_web_tutorial
"End-To-End Memory Networks" in Tensorflow
README.md
data.py
main.py
model.py
utils.py
Note_for_Colab
架設colab環境注意事項
Colab_疑難雜症
Python 2 or Python 3
Install_required_modules
Colab 系統資源
TensorFlow Basic
anaconda install
TensorFlow Operating Flow
Syntax
Tensorflow Architecture
tensorflow functions
tf.concat()
TensorFlow 疑難雜症
Graphs and Sessions in Detail (宗諭)
Supervised and Unsupervised Transfer Learning for Question Answering
Supervised_and_unsupervised_transfer_Learning_for_QA_MM_修改
Task Descriptions and Approaches
Datasets
QA Neural Network Models
End-to-End Memory Networks
Query-Based Attention CNN
Question Answering Experiments
Supervised Transfer Learning
Unsupervised Transfer Learning
參加 Kaggle 比賽
Running Python Script
Online Kernel
Offline Machine
李宏毅老師課程GC練習賽
Using Google Cloud Speech-to-Text API
Google Speech-to-Text API Example Code
gcloud Tutorial
Source Data Pre-Processing
QACNN
QACNN_paper_2017
QACNN_Algorithm
Experiment_Result_QACNN
Discussion_QACNN
QACNN Linux 實作
QACNN Linux 實作_MM_改
QACNN Colab實作
preprocess操作細節(宗諭)
main操作細節(宗諭)
QACNN_github_Coding
model/ folder
MODEL.py
def __init__(self,batch_size,x_dimension,dnn_width,cnn_filterSize,cnn_filterSize2,cnn_filterNum,cnn_filterNum2 ,learning_rate,dropoutRate,choice,max_plot_len,max_len,parameterPath)
# initialize parameters #
# CNN1 #
# CNN2 #
# compute #
Utility
output_data/ folder
plot/ folder
question/ folder
para/ folder
preprocess/ folder
plot2vec.py
qa2vec.py
utility/ folder
utility.py
import_module_batchPadding
varSentencePadding_test
train-in-utility-py-file
raw_data/ folder
plot/ folder
question/ folder
main.py file
End-To-End Memory Networks
Memory_Network_Approach
MovieQA
Story Source Data
Story JSON Files
Benchmark codes
data_loader.py
def __init__(self)
def _populate_xxxx(self)
def pprint_xxxx()
def get_xxxxx()
story_loader.py
def __init__(self)
def _check_exists(self, filename)
def _read_xxxx()
def load_story(self, movies_map, story_type='plot')
download_dvs_stories.py
Python Module Configuration
Github Configuration
Python Basic associated to MoiveQA
中文speech_recognition
Project DeepSpeech
How can I train using my own data
Kaggle Competition TensorFlow Speech Recognition Challenge
Github式介紹中文Speech recognition
pannous_tensorflow-speech-recognition
SpeechRecognition module
中文word2vector
網頁式介紹實作中文word2vector
使用word2vec訓練中文詞向量
中文word2vector_小實作_Pyladies_Taiwan
word2vec詞向量訓練及中文文本相似度計算(壹讀)
用中文資料測試 word2vec
word2vec構建中文詞向量
Github式介紹中文word2vector
Alex-CHUN-YU_Word2vec
main_Alex-Chun-yu
segmentation_Alex-Chun-yu
train_d_py
wiki-to-text-py
Genism
corpora.wikicorpus – Corpus from a Wikipedia dump
科技大擂台介紹文件_wordVector_jeiba
詞向量教學ppt
中文分詞
結巴分詞
Load customize dictionary into jieba
使用 JIEBA 結巴中文分詞程式
Chinese text segmentation
範例程式碼_jieba
Neural_word_segmentation_learning_for_chinese
Overview_Algorithm_Word_segmentation
Training_CWS
Experiment_CWS
jcyk_CWS
Colab_implement_on_CWS
Related_Work_Conclusion
LSTM_NN_Chinese_word_segmentation
中文語音Sentence Boundary Detection
Text-Domain Sentence Boundary Detection
Transcribe_file_with_word_offset Code Implementation
Program Environment Setup
Butterworth Bandpass Filter
function transcribe_file_with_word_time_offsets()
Setup Google Cloud Speech-to-Text types.RecognitionConfig
Run Google Cloud Speech Recognition
Parse Recognition Response and Save Result to excel file
Auxiliary Functions
Main block of transcribe_file_with_word_offset.py
External setup using os.environ and argparse.ArgumentParser
Get Processing File List (begin_idx and end_idx)
Set output_csv_filename and choices_list
Batch-wise Speech Transcription
Signal-Domain Sentence Segmentation
Match audio Signal (DTW)
Silence removal
Fixed sound threshold level (librosa.effects.split)
Adaptive sound threshold level
Fixed level difference to maximum sound level (pydub.silence)
Learning sound level using SVM (pyAudioAnalysis.audioSegmentation.silenceRemoval)
Acoustic-Domain Sentence Segmentation
Syllables-based Sentence Segmentation
Automatic Speech Recognition & Assessment (ASRA) Library
Google Speech-to-Text
Google Cloud Speech-to-Text API using Client Libraries
Google Cloud Speech-to-Text API using Client Libraries (on Colab)
實際操作畫面_google_speech_to_text
開通免費Google雲端服務試用Google Cloud Speech API
setup Google Cloud Service
使用Google Cloud Speech API
Google Cloud Project官網
Stackdriver Trace API
Google CLOUD SDK
Google Cloud Natural Language API Documentation
pyAudioAnalysis Library
Audio Segmentation
Supervised Audio Segmentation
Fixed-size-segment Segmentation & Classification
KNN-based segmentation & classification
HMM-based segmentation & classification
Unsupervised Audio Segmentation
Silence Removal and Event Detection
Speaker Diarization
Audio thumbnailing
Speech Recognition Wikipedia
Powered by
GitBook
AI_GC_比賽策略
比賽策略05/20~0701 2018
QACNN
中文speech recognition
中文word embedding
比賽策略03/20~05/20 2018
results matching "
"
No results matching "
"