Výsledky vyhledávání

Deep Autotuner: a Pitch Correcting Network for Singing Performances

Autor: Minje Kim, Cheng-i Wang, George Tzanetakis, Sanna Wager

Publikováno v: ICASSP

We introduce a data-driven approach to automatic pitch correction of solo singing performances. The proposed approach predicts note-wise pitch shifts from the relationship between the respective spectrograms of the singing and accompaniment. This app

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5eb9a595393a4a093a515446d27d9c77
http://arxiv.org/abs/2002.05511

Zobrazit plný text záznamu

Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning

Autor: Shiva Sundaram, Aparna Khare, Kenichi Kumatani, Sanna Wager, Minhua Wu

Publikováno v: ICASSP

In this work, we investigated the teacher-student training paradigm to train a fully learnable multi-channel acoustic model for far-field automatic speech recognition (ASR). Using a large offline teacher model trained on beamformed audio, we trained

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1049cc8615929659966571799a140729
http://arxiv.org/abs/2002.00125

Zobrazit plný text záznamu

Intonation: A Dataset of Quality Vocal Performances Refined by Spectral Clustering on Pitch Congruence

Autor: Cheng-i Wang, Sanna Wager, George Tzanetakis, John Shimmin, Stefan Sullivan, Perry R. Cook, Minje Kim

Publikováno v: ICASSP

We introduce the "Intonation" dataset of amateur vocal performances with a tendency for good intonation, collected from Smule, Inc. The dataset can be used for music information retrieval tasks such as autotuning, query by humming, and singing style

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::57594ad86bb796d1d80706f891f5a98b
https://doi.org/10.1109/icassp.2019.8683554

Zobrazit plný text záznamu

Collaborative Speech Dereverberation: Regularized Tensor Factorization for Crowdsourced Multi-Channel Recordings

Autor: Minje Kim, Sanna Wager

Publikováno v: EUSIPCO

We propose a regularized nonnegative tensor factorization (NTF) model for multi-channel speech derestriction that incorporates prior knowledge about clean speech. The approach models the problem as recovering a signal convolved with different room im

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0d442b1c6734ecd918d049087ce23506
https://doi.org/10.23919/eusipco.2018.8553565

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání