| 摘要 |
A method and an apparatus for hearing assistance, capable of compensating the lowering of the speech recognition ability related to the deterioration of the auditory sense center. The input speech is divided into voiced speech sections, unvoiced speech sections, and silent sections, of which the voiced speech sections and the silent sections are appropriately extended/contracted while the unvoiced speech sections are left unchanged, and then these sections are combined in an identical order as in the input speech, so as to obtain output speech which is easier to listen for a listener with a handicapped hearing ability. Also, only the silent sections other than the punctuation silent sections for pauses due to punctuation between sentences can be contracted and the speech speed for each of the voiced speech sections can be adjusted, and then the adjusted voiced speech sections, the unvoiced speech sections, the punctuation silent sections and the contracted silent sections can be combined in an identical order as in the input speech, in order to realize the real time hearing assistance without extending the speech utterance period. <IMAGE> |
