Wyszukiwanie zaawansowane ?

Obiekt

Preliminary Evaluation of Convolutional Neural Network Acoustic Model for Iban Language Using NVIDIA NeMo, Journal of Telecommunications and Information Technology, 20022, nr 1
Pobierz

Tytuł: Preliminary Evaluation of Convolutional Neural Network Acoustic Model for Iban Language Using NVIDIA NeMo, Journal of Telecommunications and Information Technology, 20022, nr 1

Autor:

Michael, Steve Olsen ; Mit, Edwin ; Juan, Sarah Samson

Data wydania:

2022, nr 1

Typ zasobu:

artykuł

Opis:

For the past few years, artificial neural networks (ANNs) have been one of the most common solutions relied upon while developing automated speech recognition (ASR) acoustic models. There are several variants of ANNs, such as deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs). A CNN model is widely used as a method for improving image processing performance. In recent years, CNNs have also been utilized in ASR techniques, and this paper investigates the preliminary result of an end-to-end CNN-based ASR using NVIDIA NeMo on the Iban corpus, an under-resourced language. Studies have shown that CNNs have also managed to produce excellent word error (WER) rates for the acoustic model on ASR for speech data. Conversely, results and studies concerned with under-resourced languages remain unsatisfactory. Hence, by using NVIDIA NeMo, a new ASR engine developed by NVIDIA, the viability and the potential of this alternative approach are evaluated in this paper. Two experiments were conducted: the number of resources used in the works of our ASR’s training was manipulated, as was the internal parameter of the engine used, namely the epochs. The results of those experiments are then analyzed and compared with the results shown in existing papers.

Wydawca:

Instytut Łączności - Państwowy Instytut Badawczy

Format:

application/pdf

Identyfikator zasobu:

ISSN 1509-4553, on-line: ISSN 1899-8852 ; oai:bc.itl.waw.pl:2214

Źródło:

Journal of Telecommunications and Information Technology

Język:

ang

Prawa:

Biblioteka Naukowa Instytutu Łączności

Temat i słowa kluczowe:

convolutional neural network CNN under-resourced language NVIDIA NeMo automated speech recognition acoustic modeling

Kolekcje, do których przypisany jest obiekt:

Data ostatniej modyfikacji:

11 mar 2024

Data dodania obiektu:

26 kwi 2022

Liczba wyświetleń treści obiektu:

37

Wszystkie dostępne wersje tego obiektu:

https://bc.itl.waw.pl/publication/2520

Wyświetl opis w formacie RDF:

RDF

Wyświetl opis w formacie OAI-PMH:

OAI-PMH

Nazwa wydania Data
Juan, Sarah Samson, Preliminary Evaluation of Convolutional Neural Network Acoustic Model for Iban Language Using NVIDIA NeMo, Journal of Telecommunications and Information Technology, 20022, nr 1 11 mar 2024

Obiekty Podobne

2024, nr 2, JTIT-artykuły
2024, nr 2, JTIT-artykuły
Deep Learning-based Beamforming Approach Incorporating Linear Antenna Arrays, Journal of Telecommunications and Information Technology, 2024, nr 2

Bhalke, Daulappa Paikrao, Pavan D. Anguera, Jaume

2024
artykuł
High-level and Low-level Feature Set for Image Caption Generation with Optimized Convolutional Neural Network, Journal of Telecommunications and Information Technology, 2022, nr 4

Kalla, Mukesh Sharma, Arvind Padate, Roshni Jain, Amit

2022, nr 4
artykuł
2024, nr 3, JTIT-artykuły
2024, nr 3, JTIT-artykuły
A Deep Learning-based Approach for Channel Estimation in Multi-access Multi-antenna Systems, Journal of Telecommunications and Information Technology, 2024, nr 3

Qasaymeh, Mahmoud M. Alqatawneh, Ali Khodeir, Mahmoud A. Aljaafreh, Ahmad F.

2024, nr 3
artykuł
Shallow Layer Convolutional Features with Correlation Filters for UAV Object Tracking, Journal of Telecommunications and Information Technology, 2022, nr 2

Saputri, Desti Madya Prasetyo, Agus D. Wibowo, Suryo Adhi Syihabuddin, Budi

2022, nr 2
artykuł
Deep Learning-based SNR Estimation for Multistage Spectrum Sensing in Cognitive Radio Networks, Journal of Telecommunications and Information Technology, 2022, nr 4

Patil, Vilaskumar Jeevangi, Sanjeevkumar Jawaligi, Shivkumar

2022, nr 4
artykuł
Więcej
×

Cytowanie

Styl cytowania:

Dane kontaktowe

Adres

Instytut Łączności – Państwowy Instytut Badawczy ul. Szachowa 1 04-894 Warszawa

Telefon

(+48) 5128 696

E-Mail

biblioteka@il-pib.pl

Odwiedź nas!

Ta strona wykorzystuje pliki 'cookies'. Więcej informacji