Gender adapted speech coding

Marston, David

doi:10.1109/icassp.1998.674441

Cited by 13 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is done based on the pitch information. Female and male voices show a significantly different pitch contour [6], which was found to be sufficient to make an accurate voice gender decision after a short time of speech analysis [1].…”

Section: Application Of Vgc To Voice Gender Normalisationmentioning

confidence: 93%

See 1 more Smart Citation

Application of real-time AMDF pitch-detection in a voice gender normalisation system

Jung¹,

Schwarzbacher²,

Humphreys³

et al. 2002

7th International Conference on Spoken Language Processing (ICSLP 2002)

View full text Add to dashboard Cite

Traditionally the interest in voice gender conversion was of a more theoretical nature rather than founded in reallife applications. However, with the increase in mobile communication and the resulting limitation in transmission bandwidth new approaches to minimising data rates have to be developed. Here voice gender normalisation (VGN) presents an efficient method of achieving higher compression rates by using the VGN algorithm to remove gender specific components of a speech signal and thus enhancing the information content to be transmitted.A second application for VGN is in the field of speech controlled systems, where current speech recognition algorithms have to deal with the voice characteristics of a speaker as well as the information content. Here again the use of VGN can remove the speaker's voice gender characteristics and thus enhance the message contents. Therefore, such a system would be capable of achieving higher recognition rates while being independent of the speaker. This paper presents the theory of a VGN system and furthermore, outlines an efficient real-time hardware implementation for the use in portable communications equipment.

show abstract

Section: Application Of Vgc To Voice Gender Normalisationmentioning

confidence: 93%

“…A successful implementation of a gender-dependent speech compression system is described by Marston [1]. After a gender detection step the speech is compressed using a dedicated speech encoder for the found voice gender.…”

Section: Introductionmentioning

confidence: 99%

Application of real-time AMDF pitch-detection in a voice gender normalisation system

Jung¹,

Schwarzbacher²,

Humphreys³

et al. 2002

7th International Conference on Spoken Language Processing (ICSLP 2002)

View full text Add to dashboard Cite

show abstract

“…Conventional gender recognition methods use clothing, hair style, walking, foot pressure [1,2], and voice [3], and in Ref. 2 a high recognition rate of approximately 90% was achieved.…”

Section: Introductionmentioning

confidence: 99%

A feasibility study of gender recognition with a near–infrared ray scanning spectrophotometer

Nishino

Ohshima

2011

Elect Comm in Japan

View full text Add to dashboard Cite

Male and female recognition is necessary to strengthen security and when various statistics on visitors are taken in commercial facilities and so on. The conventional method of male and female recognition currently makes use of the person's appearance, the dress, and in some cases, manner of walking, foot pressure, and hair type. But these characteristics can be intentionally changed by human intervention or design. The proposed method obtains differences in male and female characteristics from the absorbance characteristics of the fat distribution in a person's cheek, using a near‐infrared ray scanning spectrophotometer. This is a method of male and female recognition based on a new concept. Consequently, it can be used to distinguish males and females even in disguise, because it involves biometric authentication. © 2011 Wiley Periodicals, Inc. Electron Comm Jpn, 94(9): 59–68, 2011; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/ecj.10252

show abstract

“…Some studies discussed gender-related facial features in the aspect of esthetics [7]. A number of studies use other than image information: gender discrimination by voice recognition [8], perception of gender differences from walking movements [9], or studies based on measuring gender differences from joint angles during walking [10]. In the medical field, there are numerous gender-related physiological studies but few of them are noninvasive.…”

Section: Introductionmentioning

confidence: 99%

Gender recognition method based on silhouette, footstep, and foot pressure measurements for counting customers

Shibata¹,

Yamato

Tomono

et al. 2002

Electron Comm Jpn Pt II

View full text Add to dashboard Cite

SUMMARYConventional methods of gender recognition cannot be applied to counting store customers in terms of both data acquisition conditions and processing time. To solve this problem, the authors proposed a gender recognition method based on human silhouette shape characteristics. The current study demonstrated for the first time how efficient the footstep characteristic and foot pressure characteristic are for gender recognition. It discussed the recognition technique based on joining of the mentioned characteristics with the silhouette characteristic. These were joined by the one-dimensional compression based on the Fischer discrimination of characteristic vectors arranged in the order of characteristic rates for these three types. Based on the results of clothing-related research aimed at department store customers, a population group consisting of 45 male and 45 female participants was gathered to simulate distribution of various types of clothing and footwear. The authors conducted recognition tests with this population group and examined distributions by types of clothes and footwear in the characteristic space. The results showed that (1) for each separate characteristic rate the recognition rate which used to be 80% increased up to 90% due to use of joint characteristics, (2) there were numerous samples that featured correct recognition by the footstep characteristic or foot pressure characteristic even with erroneous recognition by the silhouette characteristic, which demonstrated effectiveness of the proposed combination of the three types of characteristic rates.

show abstract

Gender adapted speech coding

Cited by 13 publications

References 4 publications

Application of real-time AMDF pitch-detection in a voice gender normalisation system

Application of real-time AMDF pitch-detection in a voice gender normalisation system

A feasibility study of gender recognition with a near–infrared ray scanning spectrophotometer

Gender recognition method based on silhouette, footstep, and foot pressure measurements for counting customers

Contact Info

Product

Resources

About