Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Philippe Gournay"'
Autor:
Reza Lotfidereshgi, Philippe Gournay
Publikováno v:
ICASSP
This paper proposes a novel approach for speech signal prediction based on a recurrent neural network (RNN). Unlike existing RNN-based predictors, which operate on parametric features and are trained offline on a large collection of such features, th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1531a8a486dd3022eccf7e498301278e
http://arxiv.org/abs/2111.08116
http://arxiv.org/abs/2111.08116
Autor:
Reza Lotfidereshgi, Philippe Gournay
We propose an approach for cognitive coding of speech by unsupervised extraction of contextual representations in two hierarchical levels of abstraction. Speech attributes such as phoneme identity that last one hundred milliseconds or less are captur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9f59fc91627fd790b42acba82a020ae
Publikováno v:
MMSys
Until recently, there was no emotional speech dataset available in Canadian French. This was a limiting factor for research activities not only in Canada, but also elsewhere. This paper introduces the newly released Canadian French Emotional (CaFE) s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8e5bb39934c31fcd156d1478c237094
https://doi.org/10.1145/3204949.3208121
https://doi.org/10.1145/3204949.3208121
Publikováno v:
GlobalSIP
Audio bandwidth reduction is the very first processing step in any speech and audio coder. Its negative influence on perceived speech quality and intelligibility has been thoroughly studied and is therefore very well documented. This paper examines w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5c35ebecb32752c484d3f49188211a3
https://doi.org/10.1109/globalsip.2017.8308604
https://doi.org/10.1109/globalsip.2017.8308604
Autor:
Reza Lotfidereshgi, Philippe Gournay
Publikováno v:
ICASSP
Conventional feature-based classification methods do not apply well to automatic recognition of speech emotions, mostly because the precise set of spectral and prosodic features that is required to identify the emotional state of a speaker has not be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f82599ab4ebb130d1c0855f08f476fee
https://doi.org/10.1109/icassp.2017.7953135
https://doi.org/10.1109/icassp.2017.7953135
Publikováno v:
ISPACS
The accuracy of the reproduction of emotions by speech coders has only recently been identified as a relevant issue. Several published studies have shown that speech compression reduces the accuracy of emotions classification. These studies, however,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4d0ed4f82e3ee78da02e9ef8487e559
https://doi.org/10.1109/ispacs.2016.7824685
https://doi.org/10.1109/ispacs.2016.7824685
Publikováno v:
MMSP
Stop consonants are an important constituent of the speech signal. They contribute significantly to its intelligibility and subjective quality. However, because of their dynamic and unpredictable nature, they tend to be difficult to encode using conv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d9af6666a7f2da171881dca087e9e781
https://doi.org/10.1109/mmsp.2016.7813374
https://doi.org/10.1109/mmsp.2016.7813374
Publikováno v:
ICASSP
Although emotions play a major role in voice communication, the quality of their reproduction by low bit rate voice coders has never been investigated so far. This paper shows that the emotional state of a speaker can be identified automatically, wit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::374c55fc8062f2f5bd28dc8828ef8a86
https://doi.org/10.1109/icassp.2016.7472819
https://doi.org/10.1109/icassp.2016.7472819
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 15:2485-2495
The adaptive codebook used in code-excited linear prediction (CELP)-like speech codecs is very effective for modeling the quasi-periodic component of the excitation signal but, unfortunately, introduces a strong interframe dependency that renders the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afdf24caee238489b7f8f6e164a441d9
https://doi.org/10.1109/tasl.2007.907332
https://doi.org/10.1109/tasl.2007.907332
Autor:
Philippe Gournay, Philippe Viravau
Publikováno v:
Annales Des Télécommunications. 53:267-278
Tous les signaux modules utilises dans les activites de communication numerique sont cyclostationnaires, parce que leur fonction d’autocorrelation contient un certain nombre de periodicites temporelles appelees periodes cycliques. Dans le domaine f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f036124dc47d1911af91c8f799d651d7
https://doi.org/10.1007/bf02997683
https://doi.org/10.1007/bf02997683