In this work, natural language is explored as an interface to build paralinguistic-informed speech frameworks that can improve speech understanding and expressive speech generation and the research questions that motivate them are presented.
Shreeram Suresh Chandra· The 12th ISCA-SAC Doctoral C...· 0 citations
The loss of speech limits communication for individuals with paralysis. Direct neural-to-speech synthesis is challenging due to the limited availability of neural data for training speech brain-computer interfaces. Most existing systems rely on cascaded neural-to-text-to-speech pipelines, which increase inference laten...
A novel unsupervised domain adaptation method, Iterative Adversarial Self-Training (IAST), is proposed and results demonstrate that IAST significantly improves the generalization ability and robustness under various cross-domain settings.
Lu Sun, Shreeram Suresh Chandra, Aurosweta Mahapatra et al.· 0 citations
This work introduces AffectDF, the most comprehensive benchmark for emotionally expressive speech deepfakes, spanning TTS, VC, emotional VC, and LALM-based spoofing attacks across both acted and spontaneous emotional speech.
AFA-Net is among the first frameworks to explicitly try to combat EEG noise to improve AAD, a machine learning framework that replaces vanilla attention with a simple yet flexible differential attention mechanism to help focus on task-relevant neural activity.
Philip H. Lee, Shreeram Suresh Chandra, Karan Thakkar et al.· 0 citations
EmoSpeechBrain is introduced, a multimodal framework built on the insight that noise suppression is a precondition for effective fusion, and shows that once EEG noise is suppressed, fusion delivers gains that naive combination cannot.
Philip H. Lee, Shreeram Suresh Chandra, John H. L. Hansen· 0 citations
Brain2Speech-Net is presented, among the first single-stage frameworks to remain intelligible under limited data while removing intermediate text decoding, and achieves strong intelligibility in objective and listening tests while running faster than real time.
The role of speech preprocessing and dataset curation across widely used benchmarks for speech-based AD detection is revisited, suggesting that ``cleaner''speech datasets are not necessarily more reliable for real-world AD detection.
Lu Sun, Shreeram Suresh Chandra, Lin Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.