Leveraging Synthetic Data for Improved Manipuri-English Code-Switched ASR

Leveraging Synthetic Data for Improved Manipuri-English Code-Switched ASR

Accurately recognizing code-switched speech presents a significant challenge in the field of Automatic speech recognition (ASR), particularly for low-resource regional languages. In this work, we investigate various approaches to enhance ASR performance for code-switched Manipuri-English speech by g...

Full description

Saved in:
Bibliographic Details
Main Authors: Naorem Karline Singh, Wangkheimayum Madal, Chingakham Neeta Devi, Hoomexsun Pangsatabam, Yambem Jina Chanu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Data augmentation
natural language processing
speech recognition
synthetic text generation
Online Access:https://ieeexplore.ieee.org/document/10870319/
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items