[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fXYEfepWJp6FE_0Ub816HnVgx2cqBjfcUbbxBb2rXoNo":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2024-06-19 10:41:55",153136245,[8,9,10,11],"梯度裁剪","权重衰减","参数归一化","随机丢弃",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},18,"e435984f691240c6fc7eed81e23d857c","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F9c1e48361b00f3ee2086f4e259ed792b.jpg","语音识别综合实践案例","work_35262542","第五次作业","L1和L2正则化方法也叫做()",[21,32,35,44,53,62,70,79,88,97],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],153136244,[25,26,27,28],"语音识别","语音合成","语音增强","说话人识别","在语音领域,均方误差损失函数主要用于()","v1",0,{"answer":33,"createTime":5,"id":6,"options":34,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":36,"createTime":5,"id":37,"options":38,"question":43,"source":30,"type":31},[],153136246,[39,40,41,42],"1:1","n:m","1:n","n:1","DNN-HMM的输出节点与HMM的状态节点是()关系",{"answer":45,"createTime":5,"id":46,"options":47,"question":52,"source":30,"type":31},[],153136247,[48,49,50,51],"351","390","350","389","DNN的优势在于能够对包含多帧数据的特征进行处理,表征更丰富的语音上下文特征,DNN的输入层往往先进行多帧拼接,加入每帧语音特征39维度,对前10帧进行拼接,拼接后的特征有几维()",{"answer":54,"createTime":5,"id":55,"options":56,"question":61,"source":30,"type":31},[],153136248,[57,58,59,60],"MFCC","PLP","FBANK","以上都不对","以下哪种声学特征适合基于深度学习的语音模型()",{"answer":63,"createTime":5,"id":64,"options":65,"question":69,"source":30,"type":31},[],153136249,[66,67,68,60],"人工打标","基于其它模型输出的帧与状态的对齐文件","基于人工输出的帧与状态的对齐文件","DNN-HMM语音识别模型是有监督学习,真实标签是从哪里获取到的()",{"answer":71,"createTime":5,"id":72,"options":73,"question":78,"source":30,"type":31},[],153136250,[74,75,76,77],"1,250","1,150","50,250","50,150","假如有50个音素,每个音素有使用5个状态建模,每个音素有效发射状态是3个,那么要训练()个GMM-HMM模型,DNN-HMM的输出节点有多少个()",{"answer":80,"createTime":5,"id":81,"options":82,"question":87,"source":30,"type":31},[],153136251,[83,84,85,86],"(1,0,1)","(-1,0,-1)","(-1,0,1)","(-1,1,0)","TDNN描述当前帧与过去1帧、未来1帧拼接为3帧的节点作为输入节点的表示是()",{"answer":89,"createTime":5,"id":90,"options":91,"question":96,"source":30,"type":31},[],153136252,[92,93,94,95],"1","2","3","n","n-gram模型表示()词之间的组合概率",{"answer":98,"createTime":99,"id":100,"options":101,"question":106,"source":30,"type":31},[],"2024-06-19 10:41:56",153136253,[102,103,104,105],"ngram-count -read sample.count -order 3 -lm sample.lm","ngram-count -read sample.count -order 3 -lm sample_wb.lm -wbdiscount","ngram-count -read sample.count -order 3 -lm sample_kn.lm -interpolate -kndiscount","ngram-count -text sample.txt -order 3 -write sample.count","使用SPILM训练语言模型时,如果语料太少,可以使用以下哪种方式训练()"]