Look-ahead techniques for fast beam search

✍ Scribed by Stefan Ortmanns; Hermann Ney

• Book ID: 102566835
• Publisher: Elsevier Science
• Year: 2000
• Tongue: English
• Weight: 306 KB
• Volume: 14
• Category: Article
• ISSN: 0885-2308
• DOI: 10.1006/csla.1999.0131

✦ Synopsis

This paper presents two look-ahead techniques for speeding up large vocabulary continuous speech recognition. These two techniques are the language model look-ahead and the phoneme look-ahead; both are incorporated into the pruning process of the time-synchronous one-pass beam search algorithm. The search algorithm is based on a tree-organized pronunciation lexicon in connection with a bigram language model. Both look-ahead techniques have been tested on the 20 000-word NAB'94 task (ARPA North American Business Corpus). The recognition experiments show that the combination of bigram language model look-ahead and phoneme look-ahead reduces the size of search space by a factor of about 30 and the computational effort by a factor of 5 without affecting the word recognition accuracy in comparison with no look-ahead pruning technique.