Page: 1 2 3 4 5 6 7 8 9 10... 49
101 |
Articulatory speech synthesis ; Synthèse articulatoire de la parole
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-02433528 ; Computation and Language [cs.CL]. Université de Lorraine, 2019. English. ⟨NNT : 2019LORR0166⟩ (2019)
|
|
BASE
|
|
Show details
|
|
102 |
The Zero Resource Speech Challenge 2019: TTS without T
|
|
|
|
In: Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association ; https://hal.archives-ouvertes.fr/hal-02274112 ; Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria (2019)
|
|
BASE
|
|
Show details
|
|
103 |
Modeling Labial Coarticulation with Bidirectional Gated Recurrent Networks and Transfer Learning
|
|
|
|
In: INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-02175780 ; INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria (2019)
|
|
BASE
|
|
Show details
|
|
104 |
Conditional Variational Auto-Encoder for Text-Driven Expressive AudioVisual Speech Synthesis
|
|
|
|
In: INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association ; https://hal.inria.fr/hal-02175776 ; INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria (2019)
|
|
BASE
|
|
Show details
|
|
105 |
Features of the formation of competitive stability of enterprises of rural green tourism on the principles of marketing ...
|
|
|
|
BASE
|
|
Show details
|
|
106 |
Features of the formation of competitive stability of enterprises of rural green tourism on the principles of marketing ...
|
|
|
|
BASE
|
|
Show details
|
|
107 |
Short-Term International Experiences in Language Teacher Education: A Qualitative Meta-Synthesis
|
|
|
|
In: Australian Journal of Teacher Education (2019)
|
|
BASE
|
|
Show details
|
|
108 |
Cap-Independent mRNA Translation in Germ Cells
|
|
|
|
In: International Journal of Molecular Sciences ; Volume 20 ; Issue 1 (2019)
|
|
BASE
|
|
Show details
|
|
109 |
Improving reporting of meta-ethnography: The eMERGe reporting guidance
|
|
|
|
BASE
|
|
Show details
|
|
110 |
The views and experiences of suicidal children and young people of mental health support services: A meta-ethnography.
|
|
|
|
BASE
|
|
Show details
|
|
111 |
create_vtl_corpus: Synthesizing a speech corpus with VocalTractLab ...
|
|
|
|
BASE
|
|
Show details
|
|
112 |
Listening-test materials for "Modern speech synthesis for phonetic sciences: a discussion and an evaluation" ...
|
|
Unkn Unknown. - : University of Edinburgh. School of Informatics. Centre for Speech Technology Research (CSTR), 2019
|
|
BASE
|
|
Show details
|
|
113 |
CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92) ...
|
|
Unkn Unknown. - : University of Edinburgh. The Centre for Speech Technology Research (CSTR), 2019
|
|
BASE
|
|
Show details
|
|
115 |
Линия, цвет, слово: символы эпохи в работах молодых исследователей культуры ... : LINE, COLOR, WORD: EPOCH SYMBOLS IN YOUNG CULTURAL RESEARCHERS’ STUDIES ...
|
|
|
|
BASE
|
|
Show details
|
|
117 |
Facial re-enactment, speech synthesis and the rise of the Deepfake
|
|
|
|
In: Theses : Honours (2019)
|
|
BASE
|
|
Show details
|
|
118 |
Trans-acting translational regulatory RNA binding proteins.
|
|
|
|
BASE
|
|
Show details
|
|
119 |
Exploring Efficient Neural Architectures for Linguistic–Acoustic Mapping in Text-To-Speech
|
|
|
|
In: Applied Sciences ; Volume 9 ; Issue 16 (2019)
|
|
Abstract:
Conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models such as recurrent neural networks. Despite the good performance of such models (in terms of low distortion in the generated speech), their recursive structure with intermediate affine transformations tends to make them slow to train and to sample from. In this work, we explore two different mechanisms that enhance the operational efficiency of recurrent neural networks, and study their performance&ndash ; speed trade-off. The first mechanism is based on the quasi-recurrent neural network, where expensive affine transformations are removed from temporal connections and placed only on feed-forward computational directions. The second mechanism includes a module based on the transformer decoder network, designed without recurrent connections but emulating them with attention and positioning codes. Our results show that the proposed decoder networks are competitive in terms of distortion when compared to a recurrent baseline, whilst being significantly faster in terms of CPU and GPU inference time. The best performing model is the one based on the quasi-recurrent mechanism, reaching the same level of naturalness as the recurrent neural network based model with a speedup of 11.2 on CPU and 3.3 on GPU.
|
|
Keyword:
acoustic model; deep learning; quasi-recurrent neural networks; recurrent neural networks; self-attention; speech synthesis; text-to-speech
|
|
URL: https://doi.org/10.3390/app9163391
|
|
BASE
|
|
Hide details
|
|
120 |
Speech Synthesis in the Translation Revision Process: Evidence from Error Analysis, Questionnaire, and Eye-Tracking
|
|
|
|
In: Informatics ; Volume 6 ; Issue 4 (2019)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10... 49
|
|