DeepAI AI Chat
Log In Sign Up

SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale

by   Raphael Tang, et al.
University of Waterloo
Comcast Corporation

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes commercialization since most companies lack vast human and computational resources. In this paper, we explore training and deploying an ASR system in the label-scarce, compute-limited setting. To reduce human labor, we use a third-party ASR system as a weak supervision source, supplemented with labeling functions derived from implicit user feedback. To accelerate inference, we propose to route production-time queries across a pool of CUDA graphs of varying input lengths, the distribution of which best matches the traffic's. Compared to our third-party ASR, we achieve a relative improvement in word-error rate of 8 currently serves 12 million queries per day on our voice-enabled smart television. To our knowledge, this is the first time a large-scale, Wav2vec-based deployment has been described in the academic literature.


page 1

page 2

page 3

page 4


Streaming Voice Query Recognition using Causal Convolutional Recurrent Neural Networks

Voice-enabled commercial products are ubiquitous, typically enabled by l...

EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition

We present EasyASR, a distributed machine learning platform for training...

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

Automatic speech recognition (ASR) systems typically rely on an external...

Recent Advances in End-to-End Automatic Speech Recognition

Recently, the speech community is seeing a significant trend of moving f...

HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition

Pre-training with self-supervised models, such as Hidden-unit BERT (HuBE...

Weakly Supervised Construction of ASR Systems with Massive Video Data

Building Automatic Speech Recognition (ASR) systems from scratch is sign...

Realizing Petabyte Scale Acoustic Modeling

Large scale machine learning (ML) systems such as the Alexa automatic sp...