A Method Improves Speech Recognition with Contrastive Learning in Low-Resource Languages
Building an effective automatic speech recognition system typically requires a large amount of high-quality labeled data; However, this can be challenging for low-resource languages. Currently, self-supervised contrastive learning has shown promising results in low-resource automatic speech recognit...
Main Authors: | Lixu Sun, Nurmemet Yolwas, Lina Jiang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/8/4836 |
Similar Items
-
Combining wav2vec 2.0 Fine-Tuning and ConLearnNet for Speech Emotion Recognition
by: Chenjing Sun, et al.
Published: (2024-03-01) -
Improving Aphasic Speech Recognition by Using Novel Semi-Supervised Learning Methods on AphasiaBank for English and Spanish
by: Iván G. Torre, et al.
Published: (2021-09-01) -
Effects of Data Augmentations on Speech Emotion Recognition
by: Bagus Tris Atmaja, et al.
Published: (2022-08-01) -
Automatic Speech Disfluency Detection Using wav2vec2.0 for Different Languages with Variable Lengths
by: Jiajun Liu, et al.
Published: (2023-06-01) -
Novel Speech Recognition Systems Applied to Forensics within Child Exploitation: Wav2vec2.0 vs. Whisper
by: Juan Camilo Vásquez-Correa, et al.
Published: (2023-02-01)