Standard

Speech signals analysis using a frequency detector and smoothing first and second derivatives. / Морозов, Петр Дмитриевич; Михеев, Сергей Евгеньевич.

International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209. 2015. p. 576-579.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Harvard

Морозов, ПД & Михеев, СЕ 2015, Speech signals analysis using a frequency detector and smoothing first and second derivatives. in International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209. pp. 576-579.

APA

Морозов, П. Д., & Михеев, С. Е. (2015). Speech signals analysis using a frequency detector and smoothing first and second derivatives. In International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209 (pp. 576-579)

Vancouver

Морозов ПД, Михеев СЕ. Speech signals analysis using a frequency detector and smoothing first and second derivatives. In International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209. 2015. p. 576-579

Author

Морозов, Петр Дмитриевич ; Михеев, Сергей Евгеньевич. / Speech signals analysis using a frequency detector and smoothing first and second derivatives. International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209. 2015. pp. 576-579

BibTeX

@inproceedings{a005617e841a496daecc69596f2d7dc5,
title = "Speech signals analysis using a frequency detector and smoothing first and second derivatives",
abstract = "The amplitude and frequency analysis of continuous digital audio contained in the WAV-file of the unfixed length is produced with further playback on the basis of amplitude-frequency characteristics that are functions of time. Unlike traditionally used for this wavelets, there is no task of the original sound wave shape approximation, because the human ear cannot distinguish the shape of the sound wave, but only a set of harmonic amplitudes composing it. Therefore, negligible time outrunning or lag in phases of harmonic amplitude time-functions are acceptable, but the result of the analysis must be in a form available to change playback rate while preserving the frequency characteristics. To obtain the high quality of synthesized speech, frequency-phase detector is developed, which allows to identify the main frequency of the input digitized speech. The criterion of current quality, that lies in detector foundation, in addition to the standard deviation was enriched with penalty functions. This eliminates the",
author = "Морозов, {Петр Дмитриевич} and Михеев, {Сергей Евгеньевич}",
year = "2015",
language = "не определен",
pages = "576--579",
booktitle = "International Conference on {"}Stability and Control Processes{"} in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209",

}

RIS

TY - GEN

T1 - Speech signals analysis using a frequency detector and smoothing first and second derivatives

AU - Морозов, Петр Дмитриевич

AU - Михеев, Сергей Евгеньевич

PY - 2015

Y1 - 2015

N2 - The amplitude and frequency analysis of continuous digital audio contained in the WAV-file of the unfixed length is produced with further playback on the basis of amplitude-frequency characteristics that are functions of time. Unlike traditionally used for this wavelets, there is no task of the original sound wave shape approximation, because the human ear cannot distinguish the shape of the sound wave, but only a set of harmonic amplitudes composing it. Therefore, negligible time outrunning or lag in phases of harmonic amplitude time-functions are acceptable, but the result of the analysis must be in a form available to change playback rate while preserving the frequency characteristics. To obtain the high quality of synthesized speech, frequency-phase detector is developed, which allows to identify the main frequency of the input digitized speech. The criterion of current quality, that lies in detector foundation, in addition to the standard deviation was enriched with penalty functions. This eliminates the

AB - The amplitude and frequency analysis of continuous digital audio contained in the WAV-file of the unfixed length is produced with further playback on the basis of amplitude-frequency characteristics that are functions of time. Unlike traditionally used for this wavelets, there is no task of the original sound wave shape approximation, because the human ear cannot distinguish the shape of the sound wave, but only a set of harmonic amplitudes composing it. Therefore, negligible time outrunning or lag in phases of harmonic amplitude time-functions are acceptable, but the result of the analysis must be in a form available to change playback rate while preserving the frequency characteristics. To obtain the high quality of synthesized speech, frequency-phase detector is developed, which allows to identify the main frequency of the input digitized speech. The criterion of current quality, that lies in detector foundation, in addition to the standard deviation was enriched with penalty functions. This eliminates the

M3 - статья в сборнике материалов конференции

SP - 576

EP - 579

BT - International Conference on "Stability and Control Processes" in Memory of V.I. Zubov, SCP 2015 - Proceedings 7342209

ER -

ID: 4790744