BanSpeech: A Multi-Domain Bangla Speech Recognition Benchmark Toward Robust Performance in Challenging Conditions

BanSpeech: A Multi-Domain Bangla Speech Recognition Benchmark Toward Robust Performance in Challenging Conditions

Despite huge improvements in automatic speech recognition (ASR) employing neural networks, ASR systems still suffer from a lack of robustness and generalizability issues due to domain shifting. This is mainly because principal corpus design criteria are often not identified and examined adequately w...

Full description

Bibliographic Details
Main Authors: Ahnaf Mozib Samin, M. Humayon Kobir, Md. Mushtaq Shahriyar Rafee, M. Firoz Ahmed, Mehedi Hasan, Partha Ghosh, Shafkat Kibria, M. Shahidur Rahman
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Automatic speech recognition
Bangla
domain shifting
read speech
spontaneous speech
transfer learning
Online Access:https://ieeexplore.ieee.org/document/10453554/

Internet

https://ieeexplore.ieee.org/document/10453554/

Similar Items