research
∙
09/02/2023
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models
Since Large Language Models or LLMs have demonstrated high-quality perfo...
share
research
∙
08/31/2023
Improving vision-inspired keyword spotting using dynamic module skipping in streaming conformer encoder
Using a vision-inspired keyword spotting framework, we propose an archit...
research
∙
08/12/2023
Flexible Keyword Spotting based on Homogeneous Audio-Text Embedding
Spotting user-defined/flexible keywords represented in text frequently u...
research
∙
06/08/2023
Matching Latent Encoding for Audio-Text based Keyword Spotting
Using audio and text embeddings jointly for Keyword Spotting (KWS) has s...
research
∙
05/18/2023
PDP: Parameter-free Differentiable Pruning is All You Need
DNN pruning is a popular way to reduce the size of a model, improve the ...
research
∙
10/26/2022
HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words
Streaming keyword spotting is a widely used solution for activating voic...
research
∙
10/24/2022
I see what you hear: a vision-inspired method to localize words
This paper explores the possibility of using visual object detection tec...
research
∙
11/02/2020
Optimize what matters: Training DNN-HMM Keyword Spotting Model Using End Metric
Deep Neural Network–Hidden Markov Model (DNN-HMM) based methods have bee...
research
∙
10/20/2020
Knowledge Transfer for Efficient On-device False Trigger Mitigation
In this paper, we address the task of determining whether a given uttera...
research
∙
08/18/2020
Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation
False triggers in voice assistants are unintended invocations of the ass...
research
∙
04/25/2020
Self-supervised Learning of Visual Speech Features with Audiovisual Speech Enhancement
We present an introspection of an audiovisual speech enhancement model. ...
research
∙
01/31/2020
Detecting Emotion Primitives from Speech and their use in discerning Categorical Emotions
Emotion plays an essential role in human-to-human communication, enablin...
research
∙
01/26/2020
Multi-task Learning for Speaker Verification and Voice Trigger Detection
Automatic speech transcription and speaker recognition are usually treat...
research
∙
01/25/2020
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks
Voice-triggered smart assistants often rely on detection of a trigger-ph...
research
∙
06/28/2019