1 |
Speaker Attentive Speech Emotion Recognition
|
|
|
|
In: Proccedings of interspeech 2021 ; Interspeech 2021 ; https://hal.archives-ouvertes.fr/hal-03554368 ; Interspeech 2021, Aug 2021, Brno, Czech Republic. pp.2866-2870, ⟨10.21437/interspeech.2021-573⟩ (2021)
|
|
BASE
|
|
Show details
|
|
2 |
Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03569597 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03569608 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Beyond Voice Identity Conversion: Manipulating Voice Attributes by Adversarial Learning of Structured Disentangled Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Sequence-To-Sequence Voice Conversion using F0 and Time Conditioning and Adversarial Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Att-HACK: An Expressive Speech Database with Social Attitudes
|
|
|
|
In: Speech Prosody ; https://hal.archives-ouvertes.fr/hal-02508362 ; Speech Prosody, May 2020, Tokyo, Japan (2020)
|
|
BASE
|
|
Show details
|
|
7 |
SEQUENCE-TO-SEQUENCE MODELLING OF F0 FOR SPEECH EMOTION CONVERSION
|
|
|
|
In: IEEE International Conference on Acoustics, Speech, and Signal Processing ; https://hal.sorbonne-universite.fr/hal-02018439 ; IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2019, Brighton, United Kingdom (2019)
|
|
BASE
|
|
Show details
|
|
8 |
« The annotation of syllabic prominences and disfluencies »
|
|
|
|
In: Rhapsodie: A prosodic and syntactic treebank for spoken French. Amsterdam: Benjamins, ; https://hal.archives-ouvertes.fr/hal-03324669 ; in Lacheret, A., Kahane, S. & Pietrandrea, P. (eds). Rhapsodie: A prosodic and syntactic treebank for spoken French. Amsterdam: Benjamins,, pp.157-173, 2019 (2019)
|
|
BASE
|
|
Show details
|
|
9 |
AUTOMATIC MODELLING AND LABELLING OF SPEECH PROSODY: WHAT'S NEW WITH SLAM+ ?
|
|
|
|
In: International Congress of Phonetic Sciences (ICPhS) ; https://hal.sorbonne-universite.fr/hal-02119926 ; International Congress of Phonetic Sciences (ICPhS), Aug 2019, Melbourne, Australia (2019)
|
|
BASE
|
|
Show details
|
|
10 |
At the Interface of Speech and Music: A Study of Prosody and Musical Prosody in Rap Music
|
|
|
|
In: Speech Prosody ; https://hal.sorbonne-universite.fr/hal-01722009 ; Speech Prosody, Jun 2018, Poznan, Poland (2018)
|
|
BASE
|
|
Show details
|
|
11 |
Score-Informed Syllable Segmentation for Jingju a Cappella Singing Voice with Mel-Frequency Intensity Profiles
|
|
|
|
In: International Workshop on Folk Music Analysis ; https://hal.sorbonne-universite.fr/hal-01513160 ; International Workshop on Folk Music Analysis, Jun 2017, Malaga, Spain (2017)
|
|
BASE
|
|
Show details
|
|
12 |
Score-Informed Syllable Segmentation For Jingju A Cappella Singing Voice With Mel-Frequency Intensity Profiles ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Score-Informed Syllable Segmentation For Jingju A Cappella Singing Voice With Mel-Frequency Intensity Profiles ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Score-Informed Syllable Segmentation For Jingju A Cappella Singing Voice With Mel-Frequency Intensity Profiles ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Vers une modélisation continue de la structure prosodique: le cas des proéminences syllabiques
|
|
|
|
BASE
|
|
Show details
|
|
16 |
A Source/Filter Model with Adaptive Constraints for NMF-based Speech Separation
|
|
|
|
In: International Conference on Acoustics, Speech, and Signal Processing ; https://hal.sorbonne-universite.fr/hal-01294681 ; International Conference on Acoustics, Speech, and Signal Processing, Mar 2016, Shanghai, China (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Similarity Search of Acted Voices for Automatic Voice Casting
|
|
|
|
In: ISSN: 2329-9290 ; EISSN: 2329-9304 ; IEEE/ACM Transactions on Audio, Speech and Language Processing ; https://hal.sorbonne-universite.fr/hal-01464715 ; IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2016, 24 (9), pp.1642 - 1651. ⟨10.1109/TASLP.2016.2580302⟩ (2016)
|
|
BASE
|
|
Show details
|
|
18 |
Symbolic Modeling of Prosody: From Linguistics to Statistics
|
|
|
|
In: ISSN: 1558-7916 ; IEEE Transactions on Audio, Speech and Language Processing ; https://hal.archives-ouvertes.fr/hal-01164602 ; IEEE Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2015, 23 (3), pp.588 - 599. ⟨10.1109/TASLP.2014.2387389⟩ (2015)
|
|
BASE
|
|
Show details
|
|
19 |
Exploiting Alternatives for Text-To-Speech Synthesis: From Machine to Human
|
|
|
|
In: Speech Prosody in Speech Synthesis: Modeling and Generation of Prosody for High Quality and Flexible Speech Synthesis ; https://hal.archives-ouvertes.fr/hal-01164642 ; Springer Berlin Heidelberg. Speech Prosody in Speech Synthesis: Modeling and Generation of Prosody for High Quality and Flexible Speech Synthesis, pp.189-202, 2015, Prosody, Phonology and Phonetics, 978-3-662-45258-5. ⟨10.1007/978-3-662-45258-5_13⟩ (2015)
|
|
Abstract:
International audience ; he absence of alternatives/variants is a dramatical limitation of text-to- speech synthesis compared to the variety of human speech. This paper introduces the use of speech alternatives/variants in order to improve text-to-speech synthesis systems. Speech alternatives denote the variety of possibilities that a speaker has to pronounce a sentence - depending on linguistic constraints, specific strategies of the speaker, speaking style, and pragmatic constraints. During the training, symbolic and acoustic characteristics of a unit-selection speech synthesis system are statisti- cally modelled with context-dependent parametric models (GMMs/HMMs). During the synthesis, symbolic and acoustic alternatives are exploited using a GENERALIZED VITERBI ALGORITHM (GVA) to determine the sequence of speech units used for the synthesis. Objective and subjective evaluations support evidence that the use of speech alternatives significantly improves speech synthesis over conventional speech synthesis systems. Beyond, speech alternatives can also be used to vary the speech synthesis for a given text. The proposed method can easily be extended to HMM-based speech synthesis.
|
|
Keyword:
[INFO.INFO-SD]Computer Science [cs]/Sound [cs.SD]; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]; Prosody; Text-to-Speech
|
|
URL: https://doi.org/10.1007/978-3-662-45258-5_13 https://hal.archives-ouvertes.fr/hal-01164642 https://hal.archives-ouvertes.fr/hal-01164642/document https://hal.archives-ouvertes.fr/hal-01164642/file/springer2015_NO_CV.pdf
|
|
BASE
|
|
Hide details
|
|
20 |
The Role of Glottal Source Parameters for High-Quality Transformation of Perceptual Age
|
|
|
|
In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP) ; https://hal.archives-ouvertes.fr/hal-01164562 ; International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia (2015)
|
|
BASE
|
|
Show details
|
|
|
|