UB Paderborn / Katalog / Suche / in CDI

Sortiert nach

Einfacher Volltextzugriff von (fast) überall

Installieren Sie die LibKey Nomad-Browsererweiterung und erhalten Sie von vielen Webseiten einfachen Zugriff auf lizenzierte Volltexte oder Open Access Publikationen. Mehr erfahren...

Cross-Lingual Neural Network Speech Synthesis Based on Multiple Embeddings

International journal of interactive multimedia and artificial intelligence, 2021-12, Vol.7 (2), p.110-120

2021

Volltextzugriff (PDF)

Speaker Recognition Using Constrained Convolutional Neural Networks in Emotional Speech

Entropy (Basel, Switzerland), 2022-03, Vol.24 (3), p.414

2022

Volltextzugriff (PDF)

Enhancing Emotion Recognition through Federated Learning: A Multimodal Approach with Convolutional Neural Networks

Applied sciences, 2024-02, Vol.14 (4), p.1325

2024

Volltextzugriff (PDF)

Speaker/Style-Dependent Neural Network Speech Synthesis Based on Speaker/Style Embedding

J.UCS (Annual print and CD-ROM archive ed.), 2020-04, Vol.26 (4), p.434-453

2020

Volltextzugriff (PDF)

ЕКСПРЕСИВНИ ВИШЕЈЕЗИЧНИ СИНТЕТИЗАТОР ГОВОРА

Nosek, Tijana

2023

Volltextzugriff (PDF)

Explicit Control of the Level of Expressiveness in DNN-Based Speech Synthesis by Embedding Interpolation

Speech and Computer, 2021, Vol.12997, p.472-482

2021

Volltextzugriff (PDF)

Cross-lingual Text-to-Speech with Prosody Embedding

2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), 2023, p.1-5

2023

Volltextzugriff (PDF)

Impact of different voting strategies in CNN based speech emotion recognition

2022 30th European Signal Processing Conference (EUSIPCO), 2022, p.1174-1177

2022

Volltextzugriff (PDF)

HiFi-GAN based Text-to-Speech Synthesis in Serbian

2022 30th European Signal Processing Conference (EUSIPCO), 2022, p.1178-1182

2022

Volltextzugriff (PDF)

HiFi-GAN based Text-to-Speech Synthesis in Serbian

2022 30th European Signal Processing Conference (EUSIPCO), 2022, p.2231-2235

2022

Volltextzugriff (PDF)

Expressive multilingual speech synthesizer

2023 31st Telecommunications Forum (TELFOR), 2023, p.1-8

2023

Volltextzugriff (PDF)

Emotion recognition from speech based on ML algorithms applied on two Serbian datasets

2021 29th Telecommunications Forum (TELFOR), 2021, p.1-4

2021

Volltextzugriff (PDF)

Speech Enhancement Using Augmented SSL CycleGAN

2022 30th European Signal Processing Conference (EUSIPCO), 2022, p.1155-1159

2022

Volltextzugriff (PDF)

Initial Analysis of the Impact of Emotional Speech on the Performance of Speaker Recognition on New Serbian Emotional Database

2021 29th Telecommunications Forum (TELFOR), 2021, p.1-4

2021

Volltextzugriff (PDF)

Synthesized Speech Detection Based on Spectrogram and Convolutional Neural Networks

2019 27th Telecommunications Forum (TELFOR), 2019, p.1-4

2019

Volltextzugriff (PDF)

Towards more flexible human-machine speech communication

2023 31st Telecommunications Forum (TELFOR), 2023, p.1-4

2023

Volltextzugriff (PDF)

DNN Based Expressive Text-to-Speech with Limited Training Data

2019 27th Telecommunications Forum (TELFOR), 2019, p.1-6

2019

Volltextzugriff (PDF)

1 – 17 von 17

Suche als RSS-Feed

Suchergebnisse filtern

Filter anzeigen

Nur zeigen

Geprüft (Peer-Review)
(4)
Mit Volltextzugriff
(5)

Publikationsform

Sprache

Englisch
(16)
Serbian
(1)

Erscheinungsjahr

n.n

Thema

Neural Networks
(13)
Science & Technology
(12)
Technology
(11)
Telecommunications
(10)
Computer Science
(8)
Speech
(8)
Speech Recognition
(8)
Acoustics
(7)
Engineering
(7)
Engineering, Electrical & Electronic
(6)
Training
(6)
Computer Science, Software Engineering
(5)
Speech Synthesis
(5)
Text-To-Speech Synthesis
(5)
Artificial Neural Networks
(4)
Embedding
(4)
Emotion Recognition
(4)
Emotions
(4)
Imaging Science & Photographic Technology
(4)
Machine Learning
(4)

15 weitere anzeigen...

Weniger anzeigen...

Zeitschrift / Serie

1 weiteren anzeigen...

Weniger anzeigen...

Menü

Weitere Dienste

Einstellungen

Cross-Lingual Neural Network Speech Synthesis Based on Multiple Embeddings

Speaker Recognition Using Constrained Convolutional Neural Networks in Emotional Speech

Enhancing Emotion Recognition through Federated Learning: A Multimodal Approach with Convolutional Neural Networks

Speaker/Style-Dependent Neural Network Speech Synthesis Based on Speaker/Style Embedding

ЕКСПРЕСИВНИ ВИШЕЈЕЗИЧНИ СИНТЕТИЗАТОР ГОВОРА

Explicit Control of the Level of Expressiveness in DNN-Based Speech Synthesis by Embedding Interpolation

Cross-lingual Text-to-Speech with Prosody Embedding

Impact of different voting strategies in CNN based speech emotion recognition

HiFi-GAN based Text-to-Speech Synthesis in Serbian

HiFi-GAN based Text-to-Speech Synthesis in Serbian

Expressive multilingual speech synthesizer

Emotion recognition from speech based on ML algorithms applied on two Serbian datasets

Speech Enhancement Using Augmented SSL CycleGAN

Initial Analysis of the Impact of Emotional Speech on the Performance of Speaker Recognition on New Serbian Emotional Database

Synthesized Speech Detection Based on Spectrogram and Convolutional Neural Networks

Towards more flexible human-machine speech communication

DNN Based Expressive Text-to-Speech with Limited Training Data

Suchergebnisse filtern