I am involved in developing the following techniques:
- Speech Enhancement Using Generative Adversarial network.
- Neural network based speech enhancement using GAN under high SNR.
- Non-parallel system using Cycle GAN.
- Data augmentation for Automatic Speech Recognition.
- Data augmentation using Generative adversarial network (GAN).
- Verification of GAN based Data augmentation in Speech Recognition System.
- WaveNet as statistical Vocoder.
- Different acoustic features for WaveNet vocoder.
- Variation in data size for WaveNet vocoder
- Automatic Speech Recognition for Children.
- Prosody modifications to reduce mismatch condition
.
- Exploring different acoustic features.
- Data augmentation for improving traning data.
- Pathological speech processing.
- Enhancement of Pathological speech
.
- Analysis of Voice Disorders
.
- Classification of different categories of Pathological speech.
- Applications of Riesz transform
- Pitch estimation using Riesz transform .
- Riesz transform for statistical parametric speech synthesis.
- Speech recognition using Riesz transform.
- Glottal activity region based processing for speech synthesis
- Glottal activity detection using source features
.
- Improved voicing decision for statistical parametric speech synthesis
.
- Source modeling using features derived from glottal activity region
- Development of Text to Speech System (TTS) in Assamese and Manipuri Languages
.