CAJ | 학술논문

为满足在嵌入式系统上实现非特定人的语音识别需求，介绍一种采用离散隐马尔科夫模型(DHMM)的嵌入式语音识别系统的实现方法。设计出一种在嵌入式系统上完成语音识别功能、在PC系统上完成模板训练功能的软件架构。针对TMS320VC5509A处理器的特点，对识别软件进行实现和优化。根据语音信号不可逆的特点，提出一种优化的viterbi算法。实验结果表明，在保证识别率的条件下系统取得了200 ms以内的实时响应速度，具有很高的实用性。
위만족재감입식계통상실현비특정인적어음식별수구，개소일충채용리산은마이과부모형(DHMM)적감입식어음식별계통적실현방법。설계출일충재감입식계통상완성어음식별공능、재PC계통상완성모판훈련공능적연건가구。침대TMS320VC5509A처리기적특점，대식별연건진행실현화우화。근거어음신호불가역적특점，제출일충우화적viterbi산법。실험결과표명，재보증식별솔적조건하계통취득료200 ms이내적실시향응속도，구유흔고적실용성。
In order to meet the demand of realizing the speaker-independent speech recognition on the embedded system, a embedded speech recognition system in discrete hidden Markov model (DHMM) is proposed. The software architecture of the recognition software part running on embedded system and the training software part running on PC system are designed. According to features of TMS320VC5509A processor, the recognition software on embedded system is implemented and optimized. Also it is presented that the Viterbi algorithm is optimized on the basis of the irreversible characteristics of the speech signal. Experiments show the real-time response speed of the system achieved within 200 ms at same the recognition rate, and show its high availability.