Personalized Speech recognition on mobile devices

We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized Long Short-Term Memory (LSTM) acoustic model trained with conn...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2016-03
Main Authors: McGraw, Ian, Prabhavalkar, Rohit, Alvarez, Raziel, Montse Gonzalez Arenas, Rao, Kanishka, Rybach, David, Alsharif, Ouais, Sak, Hasim, Gruenstein, Alexander, Beaufays, Francoise, Parada, Carolina
Format: Article
Language:English
Subjects:
Bayesian analysis
Computer memory
Domains
Electronic devices
Footprints
Interpolation
Real time
Smartphones
Speech recognition
Voice recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized Long Short-Term Memory (LSTM) acoustic model trained with connectionist temporal classification (CTC) to directly predict phoneme targets, and further reduce its memory footprint using an SVD-based compression scheme. Additionally, we minimize our memory footprint by using a single language model for both dictation and voice command domains, constructed using Bayesian interpolation. Finally, in order to properly handle device-specific information, such as proper names and other context-dependent information, we inject vocabulary items into the decoder graph and bias the language model on-the-fly. Our system achieves 13.5% word error rate on an open-ended dictation task, running with a median speed that is seven times faster than real-time.
ISSN:2331-8422