FIELD: information technology.
SUBSTANCE: present invention relates to techniques for speech recognition, that is, conversion of audio signal containing speech into a transcript representation. Method comprises receiving and preliminary processing of speech signal, converting speech signal group of digital filters into frequency areas, exceeding of relative energy in time of which creates a perception of language sounds, then standardising obtained frequency area taking into account characteristics of sensitivity of volute ear frequency, amplitude and time, after which acoustic criteria of speech signal and types of sounds, finally standardising time parameters and displaying a processed voice signal.
EFFECT: technical result consists in improvement of accuracy of recognition of speech sounds.
18 cl, 7 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| SYSTEM AND METHOD OF SPEECH RECOGNITION | 2011 |
|
RU2466468C1 |
| METHOD OF RECOGNITION OF SEPARATE WORDS OF SPEECH WITH ADAPTATION TO ANNOUNCER | 1994 |
|
RU2047912C1 |
| METHOD FOR SPEECH STIMULATION IN UNLANGUAGED CHILDREN | 2014 |
|
RU2557696C1 |
| METHOD FOR HYBRID GENERATIVE-DISCRIMINATIVE SEGMENTATION OF SPEAKERS IN AUDIO-FLOW | 2013 |
|
RU2530314C1 |
| SPEECH RECOGNITION METHOD BASED ON TWO-LEVEL MORPHOPHONEMIC PREFIX GRAPH | 2015 |
|
RU2597498C1 |
| METHOD FOR PRELIMINARY PROCESSING OF TEXT | 2007 |
|
RU2386178C2 |
| METHOD OF IDENTIFYING SPEAKER FROM ARBITRARY SPEECH PHONOGRAMS BASED ON FORMANT EQUALISATION | 2009 |
|
RU2419890C1 |
| METHOD FOR AUDIO-VERBAL REHABILITATION AND DEVICE FOR IMPLEMENTATION THEREOF | 2013 |
|
RU2525366C1 |
| APPARATUS FOR TREATING THE CASES OF STAMMERING AND SPEECH DEFECTS | 2002 |
|
RU2230532C2 |
| METHOD FOR RECOGNITION OF WORDS IN CONTINUOUS SPEECH AND DEVICE WHICH IMPLEMENTS SAID METHOD | 1996 |
|
RU2101782C1 |
