tailieunhanh - Báo cáo khoa học: "Learning Sub-Word Units for Open Vocabulary Speech Recognition"

Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid word/sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems; new words can then be represented by combinations of subword units. Previous work heuristically created the sub-word lexicon from phonetic representations of text using simple statistics to select common phone sequences. . | Learning Sub-Word Units for Open Vocabulary Speech Recognition Carolina Parada1 Mark Dredze1 Abhinav Sethy2 and Ariya Rastrow1 1 Human Language Technology Center of Excellence Johns Hopkins University 3400 N Charles Street Baltimore MD USA carolinap@ mdredze@ ariya@ 2IBM . Watson Research Center Yorktown Heights NY USA asethy@ Abstract Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary many of which are information rich terms like named entities or foreign words. Hybrid word sub-word systems solve this problem by adding sub-word units to large vocabulary word based systems new words can then be represented by combinations of subword units. Previous work heuristically created the sub-word lexicon from phonetic representations of text using simple statistics to select common phone sequences. We propose a probabilistic model to learn the subword lexicon optimized for a given task. We consider the task of out of vocabulary OOV word detection which relies on output from a hybrid model. A hybrid model with our learned sub-word lexicon reduces error by and absolute at a 5 false alarm rate on an English Broadcast News and MIT Lectures task respectively. 1 Introduction Most automatic speech recognition systems operate with a large but limited vocabulary finding the most likely words in the vocabulary for the given acoustic signal. While large vocabulary continuous speech recognition LVCSR systems produce high quality transcripts they fail to recognize out of vocabulary OOV words. Unfortunately OOVs are often information rich nouns such as named entities and foreign words and mis-recognizing them can have a disproportionate impact on transcript coherence. 712 Hybrid word sub-word recognizers can produce a sequence of sub-word units in place of OOV words. Ideally the recognizer outputs a complete word for in-vocabulary IV utterances and sub-word units for OOVs. Consider the word Slobodan the

TỪ KHÓA LIÊN QUAN
crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.