中科新闻网少女舰队官网:麻烦大家帮忙翻译一段文字，计算机类的
来源：百度文库 编辑：中科新闻网 时间：2024/04/30 01:04:15
The Recognition Engine
The core speech decoder operates on finite-length segments of speech or utterances, one utterance at a time. An utterance can be upto some tens of seconds long. (Though most human-computer interactions would probably proceed in short phrases or sentences.)
Basic Recognition
Each utterance is decoded using upto three passes, two of which are optional:
· A lexical-tree Viterbi search. It produces a recognition result as well as a word lattice.
· An optional flat-structured Viterbi search restricted to the word lattice from above. It produces a new recognition result and word lattice.
· An optional global best-path search of the word lattice that produces a final result.
The optional passes improve accuracy. However, the second pass (the flat Viterbi search) can increase latency significantly. The active passes are configured once at initialization. From then on, the presence of the multiple passes is invisible to the application. It only receives the result from the final pass. However, the word lattice can subsequently searched for additional, alternative--or N-best--hypotheses by the application
The core speech decoder operates on finite-length segments of speech or utterances, one utterance at a time. An utterance can be upto some tens of seconds long. (Though most human-computer interactions would probably proceed in short phrases or sentences.)
Basic Recognition
Each utterance is decoded using upto three passes, two of which are optional:
· A lexical-tree Viterbi search. It produces a recognition result as well as a word lattice.
· An optional flat-structured Viterbi search restricted to the word lattice from above. It produces a new recognition result and word lattice.
· An optional global best-path search of the word lattice that produces a final result.
The optional passes improve accuracy. However, the second pass (the flat Viterbi search) can increase latency significantly. The active passes are configured once at initialization. From then on, the presence of the multiple passes is invisible to the application. It only receives the result from the final pass. However, the word lattice can subsequently searched for additional, alternative--or N-best--hypotheses by the application
认识引擎
核心讲话译码器操作讲话或话语的有限长度段, 一话语一次。 话语可能是一些十倍秒钟久。 (多数人计算机互作用大概虽则会进行在短的词组或句子。)
基本的认识
各话语是被解码的使用三张通行证, 二是任意的:
. 词汇树Viterbi 查寻。 它导致认识结果并且词格子。
一次任意平被构造的Viterbi 查寻对词格子制约从上述的. 。 它生产一个新认识结果和词格子。
. 导致一个最后的结果词格子的一次任意全球性佳道路查寻。
任意通行证改进准确性。 但是, 第二张通行证(平的Viterbi 查寻) 可能极大增加潜在因素。 活跃通行证被配置一次在初始化。 从然后, 多张通行证的出现是无形的对应用。 它只接受结果从最后的通行证。 但是, 词格子罐头随后寻找另外, 选择-- 或最N 佳-- 假说由应用