システム／制御／情報
Online ISSN : 2424-1806 Print ISSN : 0916-1600 ISSN-L : 0916-1600
AudioSet
A sound vocabulary and datasetAudioSet consists of an expanding ontology of 632 audio event classes and a collection of 2,084,320 human-labeled 10-second sound clips drawn from YouTube videos. The ontology is specified as a hierarchical graph of event categories, covering a wide range of human and animal sounds, musical instruments and genres, and common everyday environmental sounds. By releasing
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
AK on Twitter: "Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis pdf: https://t.co/gx4xC0fWrz abs:… https://t.co/dzJWcWz4WJ"
GitHub - masatoi/cl-libworld: A simple Common Lisp wrapper to use speech analysis library WORLD
Statistical parametric speech synthesis: from HMM to LSTM-RNN
DEEP NEURAL NETWORK (DNN) FOR TTS SYNTHESIS - Microsoft Research
