Preprint
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models
arXiv (Cornell University)
08/14/2023
DOI: 10.48550/arxiv.2308.07395
Abstract
Text injection for automatic speech recognition (ASR), wherein unpaired text-only data is used to supplement paired audio-text data, has shown promising improvements for word error rate. This study examines the use of text injection for auxiliary tasks, which are the non-ASR tasks often performed by an E2E model. In this work, we use joint end-to-end and internal language model training (JEIT) as our text injection algorithm to train an ASR model which performs two auxiliary tasks. The first is capitalization, which is a de-normalization task. The second is turn-taking prediction, which attempts to identify whether a user has completed their conversation turn in a digital assistant interaction. We show results demonstrating that our text injection method boosts capitalization performance for long-tail data, and improves turn-taking detection recall.
Details
- Title: Subtitle
- Text Injection for Capitalization and Turn-Taking Prediction in Speech Models
- Creators
- Shaan BijwadiaShuo-yiin ChangWeiran WangZhong MengHao ZhangTara N Sainath
- Resource Type
- Preprint
- Publication Details
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2308.07395
- eISSN
- 2331-8422
- Language
- English
- Date posted
- 08/14/2023
- Academic Unit
- Computer Science
- Record Identifier
- 9984696715302771
Metrics
1 Record Views