Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
2019 · Surabhi Punjabi, Harish Arsikere, Sri Garimella
Abstract
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription. In order to address this, we advocate the use of neural machine translation as a data augmentation technique for bootstrapping language models. Machine translation (MT) offers a systematic way of incorporating collections from mature, resource-rich conversational systems that may be available for a different language. However, ingesting raw translations from a general purpose MT system may not be effective owing to the presence of named entities, intra sentential code-switching and the domain mismatch between the conversational data being translated and the parallel text used for MT training. To circumvent this, we explore the following domain adaptation techniques: (a) sentence embedding based data selection for MT training, (b) model finetuning, a
Authors
(none)
Tags
Stats
Related papers
- Selecting Machine-translated Data For Quick Bootstrapping Of A Natural Language Understanding System (2018)4.52
- Bootstrap An End-to-end ASR System By Multilingual Training, Transfer Learning, Text-to-text Mapping And Synthetic Audio (2020)5.24
- Learning Domain Specific Language Models For Automatic Speech Recognition Through Machine Translation (2021)0.00
- One-to-many Multilingual End-to-end Speech Translation (2019)9.23
- Low-latency Neural Speech Translation (2018)9.03
- Instance-based Model Adaptation For Direct Speech Translation (2019)0.00
- Improving Speech Emotion Recognition In Under-resourced Languages Via Speech-to-speech Translation With Bootstrapping Data Selection (2024)7.81
- Harnessing Indirect Training Data For End-to-end Automatic Speech Translation: Tricks Of The Trade (2019)0.00