Výsledky vyhledávání

Fast Spectrogram Inversion Using Multi-Head Convolutional Neural Networks

Autor: Gregory Diamos, Heewoo Jun, Sercan O. Arik

Publikováno v: IEEE Signal Processing Letters. 26:94-98

We propose the multi-head convolutional neural network (MCNN) architecture for waveform synthesis from spectrograms. Nonlinear interpolation in MCNN is employed with transposed convolution layers in parallel heads. MCNN achieves more than an order of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2e03b5d523ee7727acf763edf8e95b52
https://doi.org/10.1109/lsp.2018.2880284

Zobrazit plný text záznamu

Language Modeling at Scale

Autor: Jiaji Huang, Kenneth Church, Md. Mostofa Ali Patwary, Milind Chabbi, Gregory Diamos, Heewoo Jun

Publikováno v: IPDPS

We show how Zipf's Law can be used to scale up language modeling (LM) to take advantage of more training data and more GPUs. LM plays a key role in many important natural language applications such as speech recognition and machine translation. Scali

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2358b96a50c59c501cef4feae411f206
http://arxiv.org/abs/1810.10045

Zobrazit plný text záznamu

Robust Speech Recognition Using Generative Adversarial Networks

Autor: Yashesh Gaur, Sanjeev Satheesh, Heewoo Jun, Anuroop Sriram

Publikováno v: ICASSP

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by learning to map

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ae4c798e5d1b5f63cac828b6e039ce8c
http://arxiv.org/abs/1711.01567

Zobrazit plný text záznamu

Cold fusion: Training Seq2seq models together with language models

Autor: Adam Coates, Sanjeev Satheesh, Anuroop Sriram, Heewoo Jun

Publikováno v: Scopus-Elsevier
INTERSPEECH

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by leveraging

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::92150346d58d51be3f85e674bbd15d08
http://www.scopus.com/inward/record.url?eid=2-s2.0-85083953079&partnerID=MN8TOARS

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání