Deep speaker: an end-to-end neural speaker embedding system
…, B Jiang, X Li, X Zhang, X Liu, Y Cao, A Kannan… - arXiv preprint arXiv …, 2017 - arxiv.org
We present Deep Speaker, a neural speaker embedding system that maps utterances to a
hypersphere where speaker similarity is measured by cosine similarity. The embeddings …
hypersphere where speaker similarity is measured by cosine similarity. The embeddings …
Deep voice 3: Scaling text-to-speech with convolutional sequence learning
We present Deep Voice 3, a fully-convolutional attention-based neural text-to-speech (TTS)
system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in …
system. Deep Voice 3 matches state-of-the-art neural speech synthesis systems in …
Machine learning enables detection of early-stage colorectal cancer by whole-genome sequencing of plasma cell-free DNA
Background Blood-based methods using cell-free DNA (cfDNA) are under development as
an alternative to existing screening tests. However, early-stage detection of cancer using …
an alternative to existing screening tests. However, early-stage detection of cancer using …
Flint: A platform for federated learning integration
…, B Chen, M Chowdhury, A Kannan… - … of Machine Learning …, 2023 - proceedings.mlsys.org
Cross-device federated learning (FL) has been well-studied from algorithmic, system scalability,
and training speed perspectives. Nonetheless, moving from centralized training to cross-…
and training speed perspectives. Nonetheless, moving from centralized training to cross-…
Quantitative criticism of literary relationships
…, T Katz, N Tripuraneni, T Dasgupta, A Kannan… - Proceedings of the …, 2017 - pnas.org
Authors often convey meaning by referring to or imitating prior works of literature, a process
that creates complex networks of literary relationships (“intertextuality”) and contributes to …
that creates complex networks of literary relationships (“intertextuality”) and contributes to …
Low-cost static gesture recognition system using MEMS accelerometers
The primary objective of the paper is to construct and test a low-cost, minimally supervised
gesture recognition system which identifies static gestures efficiently and accurately. The …
gesture recognition system which identifies static gestures efficiently and accurately. The …
Enhancing Distributed Energy Efficiency through Optimized Cluster Head Re-Election in WSNs
RV Kumar, MA Kannan… - 2024 3rd International …, 2024 - ieeexplore.ieee.org
The optimal cluster head re-election method proposed in this study offers a unique way to
improve distributed energy efficiency in Wireless Sensor Networks (WSNs). Smart energy …
improve distributed energy efficiency in Wireless Sensor Networks (WSNs). Smart energy …
Early stage colorectal cancer detection using artificial intelligence and whole-genome sequencing of cell-free DNA in a retrospective cohort of 1,040 patients: 307
Methods: De-identified plasma samples (N= 1,040) were received from academic clinical
studies and commercial biobanks (n= 579 CRC patients; n= 461 controls). Whole-genome …
studies and commercial biobanks (n= 579 CRC patients; n= 461 controls). Whole-genome …
Metric cells: Towards complete search for optimal trajectories
This paper presents a definition of convexity useful for describing local optimality in configuration
spaces, proves that finding convex regions is relatively easy, and presents an algorithm …
spaces, proves that finding convex regions is relatively easy, and presents an algorithm …
Reducing bias in production speech models
Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled
strong results in applications like speech and object recognition. However, the causality and …
strong results in applications like speech and object recognition. However, the causality and …