Search Results for author:
Found 13 papers, 1 papers with code
Modality Dropout for Multimodal Device Directed Speech Detection using Verbal and Non-Verbal Features
Device-directed speech detection (DDSD) is the binary classification task of distinguishing between queries directed at a voice assistant versus side conversation or background speech.
Streaming Anchor Loss: Augmenting Supervision with Temporal Significance
Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms.
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models
Since Large Language Models or LLMs have demonstrated high-quality performance on many complex language tasks, there is a great interest in bringing these LLMs to mobile devices for faster responses and better privacy protection.
Efficient Multimodal Neural Networks for Trigger-less Voice Assistants
The adoption of multimodal interactions by Voice Assistants (VAs) is growing rapidly to enhance human-computer interactions.
R2 Loss: Range Restriction Loss for Model Compression and Quantization
To overcome the challenge, we focus on outliers in weights of a pre-trained model which disrupt effective lower bit quantization and compression.
Ranked #1 on
Model Compression
on QNLI
Improving Voice Trigger Detection with Metric Learning
A detector is typically trained on speech data independent of speaker information and used for the voice trigger detection task.
Device-Directed Speech Detection: Regularization via Distillation for Weakly-Supervised Models
We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.
DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
For MobileNet-v1, which is a challenging DNN to compress, DKM delivers 63. 9% top-1 ImageNet1k accuracy with 0. 72 MB model size (22. 4x model compression factor).
Streaming Transformer for Hardware Efficient Voice Trigger Detection and False Trigger Mitigation
We propose a streaming transformer (TF) encoder architecture, which progressively processes incoming audio chunks and maintains audio context to perform both VTD and FTM tasks using only acoustic features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering
Our baseline is an acoustic model(AM), with BiLSTM layers, trained by minimizing the CTC loss.
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks
A pure trigger-phrase detector model doesn't fully utilize the intent of the user speech whereas by using the complete decoding lattice of user audio, we can effectively mitigate speech not intended for the smart assistant.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training
In this work, we propose and evaluate the stochastic preconditioned nonlinear conjugate gradient algorithm for large scale DNN training tasks.
Democratizing Production-Scale Distributed Deep Learning
The interest and demand for training deep neural networks have been experiencing rapid growth, spanning a wide range of applications in both academia and industry.
