Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition

04/03/2023
by   Saumya Y. Sahai, et al.
0

We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks. This architecture enables a dynamic switch for its runtime compute paths by exploiting WW spotting to select which branch of its attention networks to execute for an input audio frame. With this approach, we effectively improve WW spotting accuracy while saving runtime compute cost as defined by floating point operations (FLOPs). Using an in-house de-identified dataset, we demonstrate that the proposed dual-attention network can reduce the compute cost by 90% for WW audio frames, with only 1% increase in the number of parameters. This architecture improves WW F1 score by 16% relative and improves generic rare word error rate by 3% relative compared to the baselines.

READ FULL TEXT
research
08/03/2021

Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization

We present Bifocal RNN-T, a new variant of the Recurrent Neural Network ...
research
08/03/2021

Amortized Neural Networks for Low-Latency Speech Recognition

We introduce Amortized Neural Networks (AmNets), a compute cost- and lat...
research
11/09/2020

Efficient End-to-End Speech Recognition Using Performers in Conformers

On-device end-to-end speech recognition poses a high requirement on mode...
research
02/26/2018

Deep Feed-forward Sequential Memory Networks for Speech Synthesis

The Bidirectional LSTM (BLSTM) RNN based speech synthesis system is amon...
research
03/22/2020

High Performance Sequence-to-Sequence Model for Streaming Speech Recognition

Recently sequence-to-sequence models have started to achieve state-of-th...
research
08/27/2018

A neural attention model for speech command recognition

This paper introduces a convolutional recurrent network with attention f...
research
07/14/2023

Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning

The rapid advancement of deep neural networks has significantly improved...

Please sign up or login with your details

Forgot password? Click here to reset