Streaming End-to-end Speech Recognition For Mobile Devices

Abstract

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in real time; they must be robust to the long tail of use cases; they must be able to leverage user-specific context (e.g., contact lists); and above all, they must be extremely accurate. In this work, we describe our efforts at building an E2E speech recognizer using a recurrent neural network transducer. In experimental evaluations, we find that the proposed approach can outperform a conventional CTC-based model in terms of both latency and accuracy in a number of evaluation categories.

Stats

• citations327
• S2 citations—
• github stars0
• HF likes0
• heat score18.87
• arxiv keyhe2018streaming

Related papers

• A Streaming On-device End-to-end Model Surpassing Server-side Conventional Model Quality And Latency (2020)15.00
• Two-pass End-to-end Speech Recognition (2019)13.97
• On The Comparison Of Popular End-to-end Models For Large Scale Speech Recognition (2020)0.00
• Recognizing Long-form Speech Using Streaming End-to-end Models (2019)13.74
• Exploring Architectures, Data And Units For Streaming End-to-end Speech Recognition With Rnn-transducer (2018)16.21
• Analyzing The Quality And Stability Of A Streaming End-to-end On-device Speech Recognizer (2020)0.00
• Large-scale Multilingual Speech Recognition With A Streaming End-to-end Model (2019)14.97
• Improving RNN Transducer Modeling For End-to-end Speech Recognition (2019)0.00