Yeshanew Ale Wubet
Papers
1
Total Citations
33
H-Index
1
About
Yeshanew Ale Wubet is a researcher advancing the field of speech processing, with a primary focus on keyword recognition, voice conversion, and deep learning architectures for audio systems. His most cited work, "Voice Conversion Based Augmentation and a Hybrid CNN-LSTM Model for Improving Speaker-Independent Keyword Recognition on Limited Datasets" (2022, 33 citations), addresses a critical challenge in speech technology: achieving robust, speaker-independent keyword spotting with scarce training data. Wubet introduced a novel approach that leverages voice conversion to augment limited datasets, combined with a hybrid CNN-LSTM model that captures both spatial and temporal features in speech signals. This innovation significantly improves recognition accuracy, making it highly relevant for applications in keyword spotting, robotics, and smart home surveillance. By tackling data scarcity—a common bottleneck in real-world deployments—his work offers a practical solution for building more reliable, scalable voice-controlled systems. Wubet’s contributions are shaping the development of efficient, speaker-agnostic speech interfaces, and his research continues to influence the intersection of data augmentation and deep learning in audio processing.
Research Focus
Key Achievements
Top Papers
- 1