Deep learning of split temporal context for automatic speech recognition

Autor: Olivier Le Blouch, Benoit Besset, Patrice Collen, Moez Baccouche

Publikováno v: ICASSP

This paper follows the recent advances in speech recognition which recommend replacing the standard hybrid GMM/HMM approach by deep neural architectures. These models were shown to drastically improve recognition performances, due to their ability to

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::4daaa3a0b6bde2b1c5166ff955a7df5c
https://doi.org/10.1109/icassp.2014.6854639

Estimation of Frequency for AM/FM Models Using the Phase Vocoder Framework

Autor: Patrice Collen, Michaël Betser, Gael Richard, Bertrand David

Publikováno v: IEEE Transactions on Signal Processing
IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2008, 56, ⟨10.1109/TSP.2007.906768⟩

International audience; This paper proposes an extension of the applicability of phase-vocoder-based frequency estimators for generalized sinusoidal models, which include phase and amplitude modulations. A first approach, called phase corrected vocod

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f1f4e5ad2ba81d45fc5ebb76f996d1ee
https://hal.inria.fr/hal-02652652