Akira Tamamori

speech_process_exercise. 音声情報処理n本ノックを目指して

ace-isearch. A seamless bridge between isearch, ace-jump-mode, avy, and helm-swoop.

zoneout-tensorflow. An implementation of zoneout regularizer on LSTM-RNN by Tensorflow

recurrent-batchnorm-tensorflow. An implementation of LSTM with Recurrent Batch Normalization.

multiplicative-lstm-tensorflow. An implementation of multiplicative LSTM in TensorFlow

dcase2020_task2_baseline. DCASE2020 Challenge Task 2 baseline system

benzaiten_pytorch. Python

music_process_exercise. 音楽情報処理n本ノックを目指して

onoma-to-wave. Unofficial implementations of Onoma-to-Wave

onoma-to-wave_transformer. Unofficial implementations of environmental sound synthesis system with Transformer

music-esprit-python. A Python toolkit for modern high-resolution spectral estimation, covering subspace (MUSIC, ESPRIT), AR (HOYW), and iterative (RELAX, CFH, NOMP) methods.

dcase2021_task2_baseline_ae. Autoencoder-based baseline system for DCASE2021 Challenge Task 2.

dcase2021_task2_baseline_mobile_net_v2. MobileNetV2-based baseline system for DCASE2021 Challenge Task 2.

topr. Two-stage Online/Offline Phase Reconstruction (TOPR)

avy-migemo. avy with migemo

emotion_separator. Provides a neural network which implements a functionarity to separate the emotional component from the x-vector.

von-mises. Unofficial implementation of phase reconstruction method with von Mises distribution DNN

swiper-migemo. Use ivy/counsel/swiper with migemo.

ag-a-lot. manages multiple search results buffers for ag.el

minimal-sqvae. A minimal Pytorch Implementation of Stochastically Quantized Variational AutoEncoder (SQ-VAE) by Sony

topr_lj. Two-stage Online/Offline Phase Reconstruction (TOPR) on the LJ Speech Dataset.

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

emacs-color-theme-solarized. Emacs highlighting using Ethan Schoonover’s Solarized color scheme

tensorflow_with_latest_papers. Implementation of Newest RNN and Seq2Seq Features

elscreen. Emacs window session manager like GNU screen

rpu. Unofficial implementation of phase reconstruction method based on recurrent phase unwrapping with DNNs

diffusion-model-book. Jupyter Notebook

babiniku. C++

wav2pix. Speech-conditioned face generation using Generative Adversarial Networks (ICASSP 2019)

keras. Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on TensorFlow or Theano.

ace-region. A utility for region expansion by using ace-jump-mode.

beginning_asa. ひたすら楽して音響信号解析：プログラム置き場

chord2melody. Python

speech-synth. A wrapper for Flite+hts_engine and Open JTalk on Emacs.