Improving Proper Noun Recognition in End-to-End ASR By Customization of the MWER Loss Criterion
| Autor: | Cal Peyser, Tara N. Sainath, Golan Pundak |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Machine Learning Training set Computer science business.industry Inference Word error rate Pronunciation computer.software_genre Computer Science - Sound Personalization Machine Learning (cs.LG) End-to-end principle Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering Proper noun Artificial intelligence Language model business computer Natural language processing Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | ICASSP |
| Popis: | Proper nouns present a challenge for end-to-end (E2E) automatic speech recognition (ASR) systems in that a particular name may appear only rarely during training, and may have a pronunciation similar to that of a more common word. Unlike conventional ASR models, E2E systems lack an explicit pronounciation model that can be specifically trained with proper noun pronounciations and a language model that can be trained on a large text-only corpus. Past work has addressed this issue by incorporating additional training data or additional models. In this paper, we instead build on recent advances in minimum word error rate (MWER) training to develop two new loss criteria that specifically emphasize proper noun recognition. Unlike past work on this problem, this method requires no new data during training or external models during inference. We see improvements ranging from 2% to 7% relative on several relevant benchmarks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|