Tone-enhanced generalized character posterior probability (GCPP) for Cantonese LVCSR

Ye, Qian; Soong, Frank K.; Lee, Tan

doi:10.1016/j.csl.2007.12.003

Cited by 6 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With similar assumptions for the character edges e 2 and e 3 , we have P (e 2 |A) ≈ P (e 3 |A) ≈ P (e|A). Similar results were obtained by Yao et al (2008) from a different point of view.…”

Section: Character Posterior Probability and Character-based Confusion Network (Ccn)supporting

confidence: 89%

“…P (H) is the language model score of H (after proper scaling) and P (A|H) is the acoustic model score. CCN was known to be very helpful in reducing character error rate (CER) since it minimizes the expected CER (Fu et al, 2006;Qian et al, 2008). Given a CCN, we simply choose the characters with the highest PP from each cluster as the recognition results.…”

Section: Character Posterior Probability Andmentioning

confidence: 99%

“…After we obtain the PPs for each character arc in the lattice, such as P (e i |A) as mentioned above, we can perform the same clustering method proposed by Mangu et al (2000) to convert the word lattice to a strict linear sequence of clusters, each consisting of a set of alternatives of character hypotheses, or a character-based confusion network (CCN) (Fu et al, 2006;Qian et al, 2008). In CCN we collect the PPs for all character arc c with beginning time τ and end time t as P ([c; τ, t]|A) (based on the above mentioned approximation):…”

Section: Character Posterior Probability Andmentioning

confidence: 99%

“…Based on a baseline lexicon (Lex 0 ) and a language model (LM 0 ) we perform ASR on the adaptation corpus and construct corresponding word lattices. We then build character-based confusion networks (CCNs) (Fu et al, 2006;Qian et al, 2008). On the CCNs we perform the proposed algorithm to add and delete words into/from the current lexicon.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Discriminative lexicon adaptation for improved character accuracy

Pan

Lee

Furui

2009

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural

View full text Add to dashboard Cite

While OOV is always a problem for most languages in ASR, in the Chinese case the problem can be avoided by utilizing character n-grams and moderate performances can be obtained. However, character ngram has its own limitation and proper addition of new words can increase the ASR performance. Here we propose a discriminative lexicon adaptation approach for improved character accuracy, which not only adds new words but also deletes some words from the current lexicon. Different from other lexicon adaptation approaches, we consider the acoustic features and make our lexicon adaptation criterion consistent with that in the decoding process. The proposed approach not only improves the ASR character accuracy but also significantly enhances the performance of a characterbased spoken document retrieval system.

show abstract

Section: Character Posterior Probability and Character-based Confusion Network (Ccn)supporting

confidence: 89%

Section: Character Posterior Probability Andmentioning

confidence: 99%

Section: Character Posterior Probability Andmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Discriminative lexicon adaptation for improved character accuracy

Pan

Lee

Furui

2009

Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural

View full text Add to dashboard Cite

show abstract

“…Some works have also been reported on Asian tone languages such as Mandarin [6,14,16,19,23,31,32] Cantonese [15,21,22,25,63] and Thai [39,59]. Ray and Ghoshal [26] have also reported the development an ASR for vowels of three Indian languages, namely: Telugu, Assamese and Bengali and Salor et al [60] have reported works on Turkish.…”

Section: Introductionmentioning

confidence: 91%