ASR Error Correction and Domain Adaptation Using Machine Translation

Autor:	Mani, Anirudh, Palaskar, Shruti, Meripo, Nimshi Venkat, Konam, Sandeep, Metze, Florian
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning Computer Science - Sound Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Off-the-shelf pre-trained Automatic Speech Recognition (ASR) systems are an increasingly viable service for companies of any size building speech-based products. While these ASR systems are trained on large amounts of data, domain mismatch is still an issue for many such parties that want to use this service as-is leading to not so optimal results for their task. We propose a simple technique to perform domain adaptation for ASR error correction via machine translation. The machine translation model is a strong candidate to learn a mapping from out-of-domain ASR errors to in-domain terms in the corresponding reference files. We use two off-the-shelf ASR systems in this work: Google ASR (commercial) and the ASPIRE model (open-source). We observe 7% absolute improvement in word error rate and 4 point absolute improvement in BLEU score in Google ASR output via our proposed method. We also evaluate ASR error correction via a downstream task of Speaker Diarization that captures speaker style, syntax, structure and semantic improvements we obtain via ASR correction. Comment: Accepted for Oral Presentation at ICASSP 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2003.07692 Zobrazit plný text záznamu View this record from Arxiv