洞察力 发表于 2025-3-23 09:54:31

Hybrid Connectionist Models For Continuous Speech Recognition,nd flexible, but the probability estimation techniques used with these models typically suffer from a number of significant limitations. Over the last few years, we have demonstrated that fairly simple Multi-Layered Perceptrons (MLPs) can be discriminatively trained to estimate emission probabilitie

Arb853 发表于 2025-3-23 16:09:17

Automatic Generation of Detailed Pronunciation Lexicons,the source of sub-words units for which we build acoustic models (1) a coarse phonemic representation, (2) a single, fine phonetic realization, and (3) multiple phonetic realizations with associated likelihoods. We describe how we obtain these different pronunciations from text-to-speech systems and

absolve 发表于 2025-3-23 21:26:54

http://reply.papertrans.cn/17/1665/166452/166452_13.png

五行打油诗 发表于 2025-3-24 01:30:44

http://reply.papertrans.cn/17/1665/166452/166452_14.png

Acupressure 发表于 2025-3-24 06:20:18

http://reply.papertrans.cn/17/1665/166452/166452_15.png

panorama 发表于 2025-3-24 09:21:57

Dynamic Programming Search Strategies: From Digit Strings to Large Vocabulary Word Graphs,basic one-pass algorithm for word string recognition, we extend the search strategy to vocabularies of 20,000 words and more by using a tree organization of the vocabulary. Finally, we describe how this predecessor conditioned algorithm can be refined to produce high-quality word graphs. This method

极小 发表于 2025-3-24 13:09:37

Multiple-Pass Search Strategies,ially, without any increase in error rate. We consider two basic strategies: the N-best Paradigm, and the Forward-Backward search. Both of these strategies operate on the entire sentence in (at least) two passes. The N-best Paradigm computes alternative hypotheses for a sentence, which can later be

傲慢物 发表于 2025-3-24 17:10:24

http://reply.papertrans.cn/17/1665/166452/166452_18.png

惩罚 发表于 2025-3-24 22:47:44

http://reply.papertrans.cn/17/1665/166452/166452_19.png

Anemia 发表于 2025-3-25 00:02:44

http://reply.papertrans.cn/17/1665/166452/166452_20.png
页: 1 [2] 3 4 5 6 7
查看完整版本: Titlebook: Automatic Speech and Speaker Recognition; Advanced Topics Chin-Hui Lee,Frank K. Soong,Kuldip K. Paliwal Book 1996 Kluwer Academic Publisher