Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR

no code implementations • 21 Oct 2022 • Pranay Dighe, Prateeth Nayak, Oggi Rudovic, Erik Marchi, Xiaochuan Niu, Ahmed Tewfik

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 interactions with the VA. To this end, we present a novel approach to predict the user's intent (the user speaking to the device or not) directly from acoustic and textual information encoded at subword tokens which are obtained via an end-to-end ASR model.

intent-classification Intent Classification

Improving Voice Trigger Detection with Metric Learning

no code implementations • 5 Apr 2022 • Prateeth Nayak, Takuya Higuchi, Anmol Gupta, Shivesh Ranjan, Stephen Shum, Siddharth Sigtia, Erik Marchi, Varun Lakshminarasimhan, Minsik Cho, Saurabh Adya, Chandra Dhir, Ahmed Tewfik

A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task.

Metric Learning

Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

no code implementations • 21 Nov 2020 • Karan Sikka, Jihua Huang, Andrew Silberfarb, Prateeth Nayak, Luke Rohrer, Pritish Sahu, John Byrnes, Ajay Divakaran, Richard Rohwer

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs.

Common Sense Reasoning Zero-Shot Learning

Bit Efficient Quantization for Deep Neural Networks

no code implementations • 7 Oct 2019 • 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.

Clustering Quantization