Google Research

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接

An annotated implementation of the Transformer paper.

Reference models and tools for Cloud TPUs.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)

Google Colaboratory Notebooks and Repositories (by @firmai)

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Dataset to assess the disentanglement properties of unsupervised learning methods

💻 🤖 A summary on our attempts at using Deep Learning approaches for Emotional Text to Speech 🔈

Lightweight and Interpretable ML Model for Speech Emotion Recognition and Ambiguity Resolution (trained on IEMOCAP dataset)

Text to Speech with PyTorch (English and Mongolian)

Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"

Multispeaker & Emotional TTS based on Tacotron 2 and Waveglow

Detecting emotions using MFCC features of human speech using Deep Learning

Calculation of MCD (dB) between two speech waveforms

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

CSA Lecture "Information Compression in Computational Science" (計算科学における情報圧縮)

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Implementation of "Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis"