Abstract | ||
---|---|---|
This paper investigates methods for coping with out-of-vocabulary words in a large vocabulary speech recognition task, namely the automatic transcription of Italian broadcast news. Two alternative ways for augmenting a 64K(thousand)-word recognition vocabulary and language model are compared: introducing extra words with their phonetic transcription up to 1.2M (million) words, or extending the language model with so-called graphones, i.e. subword units made of phone-character sequences. Graphones and phonetic transcriptions of words are automatically generated by adapting an off-the-shelf statistical machine translation toolkit. We found that the word-based and graphone-based extensions allow both for better recognition performance, with the former performing significantly better than the latter. In addition, the word-based extension approach shows interesting potential even under conditions of little supervision. In fact, by training the grapheme to phoneme translation system with only 2K manually verified transcriptions, the final word error rate increases by just 3% relative, with respect to starting from a lexicon of 64K words. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICASSP.2009.4960583 | ICASSP |
Keywords | Field | DocType |
extra word,word recognition vocabulary,final word error rate,language model,large vocabulary speech recognition,off-the-shelf statistical machine translation,phonetic transcription,huge vocabulary asr,out-of-vocabulary word,automatic transcription,better recognition performance,documentation,natural languages,data mining,speech,speech processing,broadcasting,decoding,automatic speech recognition,training data,word error rate,statistical analysis,speech recognition,word recognition,language translation,hidden markov models,art,robustness | Language translation,Phonetic transcription,Computer science,Word recognition,Word error rate,Speech recognition,Lexicon,Natural language processing,Artificial intelligence,Vocabulary,Language model,Stop words | Conference |
ISSN | Citations | PageRank |
1520-6149 | 7 | 0.52 |
References | Authors | |
8 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Matteo Gerosa | 1 | 172 | 13.14 |
marcello federico | 2 | 2420 | 179.56 |