Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Jouni Paulus"'
Autor:
Jouni Paulus, Anssi Klapuri
Publikováno v:
EURASIP Journal on Audio, Speech, and Music Processing, Vol 2009 (2009)
This paper proposes a method for transcribing drums from polyphonic music using a network of connected hidden Markov models (HMMs). The task is to detect the temporal locations of unpitched percussive sounds (such as bass drum or hi-hat) and recognis
Externí odkaz:
https://doaj.org/article/99118af33b354b8db6a459095ea81b56
Autor:
Jouni Paulus, Matteo Torcoli
A geometrically-motivated method for primary-ambient decomposition is proposed and evaluated in an up-mixing application. The method consists of two steps, accommodating a particularly intuitive explanation. The first step consists of signal-adaptive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::26113876036cbee061c0b295d2f7e51e
http://arxiv.org/abs/2206.02125
http://arxiv.org/abs/2206.02125
Autor:
Jouni Paulus, David Geary, Christian Simon, Ben Shirley, Alessandro Travaglini, Matteo Torcoli, Davide Straninger
Publikováno v:
Journal of the Audio Engineering Society. 68:810-818
Voice-over-Voice (VoV) is a common mixing practice observed in news reports and docu- mentaries, where a foreground voice is mixed on top of a background voice, e.g., to translate an interview. This is achieved by ducking the background voice so that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04f27b7eed424ce4a88e880c8909dd26
https://doi.org/10.17743/jaes.2020.0022
https://doi.org/10.17743/jaes.2020.0022
Publikováno v:
Interspeech 2021.
This paper describes a hands-on comparison on using state-of-the-art music source separation deep neural networks (DNNs) before and after task-specific fine-tuning for separating speech content from non-speech content in broadcast audio (i.e., dialog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c2758fb6536e1a243d9fe86f8412ce6
https://doi.org/10.21437/interspeech.2021-1418
https://doi.org/10.21437/interspeech.2021-1418
Publikováno v:
ICASSP
Speech enhancement attenuates interfering sounds in speech signals but may introduce artifacts that perceivably deteriorate the output signal. We propose a method for controlling the trade-off between the attenuation of the interfering background sig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95502966baf36ef238b0fbe0a415db68
http://arxiv.org/abs/2107.10562
http://arxiv.org/abs/2107.10562
Remixing separated audio sources trades off interferer attenuation against the amount of audible deteriorations. This paper proposes a non-intrusive audio quality estimation method for controlling this trade-off in a signal-adaptive manner. The recen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7f60885b1cff728f06d8863f052ac74d
http://arxiv.org/abs/2107.10151
http://arxiv.org/abs/2107.10151
Publikováno v:
Journal of the Audio Engineering Society. 67:1003-1011
In audio production, background ducking facilitates speech intelligibility while allowing the background to fulfill its purpose, e.g., to create ambience, set the mood, or convey semantic cues. Technical details for recommended ducking practices are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d2c6b113ef335bf2d52c48d2b1b8412
https://doi.org/10.17743/jaes.2019.0052
https://doi.org/10.17743/jaes.2019.0052
Low intelligibility of narration or dialogue resulting from high background level is one of the most common complaints in broadcasting. Even when the intelligibility is not compromised, listeners may have personal preferences that differ from the mix
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6093152fb3e9b806b460f927517d0bc2
https://publica.fraunhofer.de/handle/publica/259079
https://publica.fraunhofer.de/handle/publica/259079
Media consumption in broadcasting is heading towards high degrees of content personalization also in audio thanks to next-generation audio systems. It is thus crucial to assess the benefit of personalized media delivery. To this end, the adjustment/s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b0de4179d0e0a9a5cb09f8c6616404d
https://publica.fraunhofer.de/handle/publica/256418
https://publica.fraunhofer.de/handle/publica/256418
Publikováno v:
EUSIPCO
The spectral envelope of a speech signal encodes information about the characteristics of the speech source. As a result, spectral envelope modeling is a central task in speech applications, where tracking temporal transitions in diphones and triphon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a6d65706f1323d1331047b9fb95e3e0
https://doi.org/10.23919/EUSIPCO.2017.8081483
https://doi.org/10.23919/EUSIPCO.2017.8081483