Speech recognition using neural networks - Chapter 5 doc
Speech recognition using neural networks - Chapter 5 doc
... no English. Janus performs speech trans- lation by integrating three modules — speech recognition, text translation, and speech gen- eration — into a single end-to-end system. Each of these modules ... The speech recognition module, for exam- ple, was originally implemented by our LPNN, described in Chapter 6 (Waibel et al 1991, Osterholtz et al 1992); but it was later replaced b...
Ngày tải lên: 13/08/2014, 02:21
Speech recognition using neural networks - Chapter 6 pps
... HMMs using a single gaussian mixture, vs. LPNN. perplexity System 7 111 402 HMM-1 55 % HMM -5 96% 70% 58 % HMM-10 97% 75% 66% LVQ 98% 80% 74% LPNN 97% 60% 40% Table 6.4: Word accuracy of HMM-n with ... (99%) 2 49 /50 (98%) 20/20 (100%) 229/229 (100%) 3 50 /50 (100%) 20/20 (100%) 229/229 (100%) 924 1 106/118 (90%) 55 /60 (92%) 855 /900 ( 95% ) 2 116/118 (98%) 58 /60 (97%) 886/900 (98%)...
Ngày tải lên: 13/08/2014, 02:21
Speech recognition using neural networks - Chapter 7 pdf
... training of a speech recognizer?” 7 .5. Summary 143 7 .5. Summary In this chapter we have seen that good word recognition accuracy can be achieved using neural networks that have been trained as speech ... helpful. 0 10 20 30 40 50 60 70 80 word accuracy (%) 0 1 2 3 4 5 6 7 8 9 10 epochs PLP input normalization (May6) stdev 2 stdev 1.0 stdev .5 stdev . 25 stdev .1 25 No n...
Ngày tải lên: 13/08/2014, 02:21
Speech recognition using neural networks - Chapter 8 potx
... in Chapter 7 were developed on this database, and were never applied to the Conference Registration database. perplexity test on training set System 7 111 402(a) 402(b) 111 HMM-1 55 % HMM -5 96% ... 402(b) 111 HMM-1 55 % HMM -5 96% 71% 58 % 76% HMM-10 97% 75% 66% 82% LPNN 97% 60% 41% HCNN 75% LVQ 98% 84% 74% 61% 83% TDNN 98% 78% 72% 64% MS-TDNN 98% 82% 81% 70% 85% Table 8.1: Comparat...
Ngày tải lên: 13/08/2014, 02:21
Speech recognition using neural networks - Chapter 9 pptx
... 1 1-1 5 temporal constraints 1 2-1 3, 16 dynamics 30, 78, 118 integration 38, 53 , 54 , 56 , 11 1-2 , 13 8-9 modeling 7, 1 2-1 3, 16, 5 6 -5 7, 151 , 154 structure 56 variability 1, 4, 5 6 -5 7 tensor products 57 testing ... 103, 11 9-1 20, 138 state of the art. See speech recognition static classification 51 , 52 , 5 5- 5 7 statistical models 4, 1 5- 2...
Ngày tải lên: 13/08/2014, 02:21
speech recognition using neural networks
... performance. We will see that neural networks help to avoid this problem. 1.2. Neural Networks Connectionism, or the study of artificial neural networks, was initially inspired by neuro- biology, but it ... advocates. Figure 2.1: Structure of a standard speech recognition system. Figure 2.2: Signal analysis converts raw speech to speech frames. raw speech signal analysis...
Ngày tải lên: 28/04/2014, 10:18