11 citations · 18 across the 6 of their papers we have counts for
6 papers
RepCNN: Micro-sized, Mighty Models for Wakeword Detection
Arnav Kundu, Prateeth Nayak, Priyanka Padmanabhan +1
Always-on machine learning models require a very low memory and compute footprint. Their restricted parameter count limits the model's capacity to learn, and the effectiveness of t…
Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR
Pranay Dighe, Prateeth Nayak, Oggi Rudovic +3
Accurate prediction of the user intent to interact with a voice assistant (VA) on a device (e.g. on the phone) is critical for achieving naturalistic, engaging, and privacy-centric…
Improving Voice Trigger Detection with Metric Learning
Prateeth Nayak, Takuya Higuchi, Anmol Gupta +9
Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data…
Transformer Based Molecule Encoding for Property Prediction
Prateeth Nayak, Andrew Silberfarb, Ran Chen +2
Neural methods of molecule property prediction require efficient encoding of structure and property relationship to be accurate. Recent work using graph algorithms shows limited ge…
Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
Karan Sikka, Jihua Huang, Andrew Silberfarb +6
We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as nov…
Bit Efficient Quantization for Deep Neural Networks
Prateeth Nayak, David Zhang, Sek Chai
Quantization for deep neural networks have afforded models for edge devices that use less on-board memory and enable efficient low-power inference. In this paper, we present a comp…