A lexicon learning-based heliumspeech unscrambling method in saturation diving, applicable to a system comprising at least one diver, one heliumspeech correction network, and one heliumspeech unscrambling network, wherein a heliumspeech signal of the diver is S, and the heliumspeech unscrambling method comprises the following steps:
- first stage—learning of the correction network
- step 1. lexicon signal construction—constructing a common working language lexicon K of the diver for saturation diving operation according to saturation diving specifications;
- step 2. supervision signal generation—reading, by the diver i, words in the lexicon K in a normal atmospheric environment to obtain supervision signals Xi, to generate a supervision signal set X={Xi} of the correction network for machine learning, wherein i=1, 2, . . . , I, and I is a number of divers;
- step 3. vector signal generation—reading, by the diver i, the words in the lexicon K respectively in environments corresponding to saturation diving depths h1, h2, h3, . . . , hL, to obtain vector signals Yi, 1, wherein l=1, 2, . . . , L, and L is a number of heliumspeech test points, to generate a vector signal set Y={Yi, 1} of the correction network for machine learning;
- step 4. learning of the correction network—performing, by the correction network, supervised learning by using the vector signals Yi, 1 as input signals and the supervision signals Xi as expected output signals to form a correction network parameter set C={Ci, 1} corresponding to the vector signals Yi, 1;
- second stage—heliumspeech unscrambling
- step 5. correction network parameter selection—fitting the heliumspeech signal S of the diver during saturation diving operation with all the vector signals Yi, 1 in the vector signal set Y, and selecting a parameter Cn, 1 corresponding to a vector signal Yn, 1 having the highest fitness as a correction network parameter;
- step 6. heliumspeech correction—correcting the heliumspeech signal S by using the heliumspeech signal S as an input signal of the correction network, to generate a corrected speech signal T;
- step 7. learning of the unscrambling network—comparing speeches in the corrected speech signal T with speeches in the supervision signals in the supervision signal set X of the correction network for machine learning word by word, to calculate fitnesses therebetween;
- selecting, from the supervision signal set X, speeches corresponding to words having the highest fitnesses;
- matching the selected speeches with speeches corresponding to the words in the corrected speech signal T into groups;
- sorting, in descending order by fitness, the matched speeches of the groups;
- selecting the top p % of the groups in orders of the fitness;
- taking speeches in the corrected speech signal T in the selected top p % of the groups as a vector signal U of the unscrambling network for machine learning and taking speeches corresponding to words in the supervision signal set X in the selected top p % of the groups as a supervision signal V of the unscrambling network for machine learning, and
- performing, by the unscrambling network, supervised learning;
- and
- step 8. heliumspeech unscrambling—unscrambling the heliumspeech S by using the corrected speech signal T as an input signal of the unscrambling network.