Respiratory Activity in Speech

Ohala, John J.

doi:10.1007/978-94-009-2037-8_2

Cited by 52 publications

(27 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Natural speech is primarily realized by movement of articulators that convert DC pressure variations created during respiration into AC pressure variations or speech sounds [45]. Alter- natively, there is an interaction between pulmonic and oral systems during speech production.…”

Section: Analysis Of the Discriminationmentioning

confidence: 99%

“…As a consequence, the proposed approach could be detecting logical access attacks on the basis of the effect of interaction between pulmonic and oral systems that exists in the natural speech but not in the synthetic or voice converted speech (due to source-system modeling and subsequent processing). It is understood that the interaction between pulmonary and oral cavity systems can create DC effects when producing sounds such as clicks, ejectives, implosives [45]. Furthermore, human breath in the respiration process can reach the microphone and appear as "pop noise" [22], which again manifests in the very low frequency region.…”

Section: Analysis Of the Discriminationmentioning

confidence: 99%

See 1 more Smart Citation

Long-Term Spectral Statistics for Voice Presentation Attack Detection

Muckenhirn

Korshunov

Magimai-Doss

et al. 2017

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Automatic speaker verification systems can be spoofed through recorded, synthetic or voice converted speech of target speakers. To make these systems practically viable, the detection of such attacks, referred to as presentation attacks, is of paramount interest. In that direction, this paper investigates two aspects: (a) a novel approach to detect presentation attacks where, unlike conventional approaches, no speech signal related assumptions are made, rather the attacks are detected by computing first order and second order spectral statistics and feeding them to a classifier, and (b) generalization of the presentation attack detection systems across databases. Our investigations on Interspeech 2015 ASVspoof challenge dataset and AVspoof dataset show that, when compared to the approaches based on conventional short-term spectral processing, the proposed approach with a linear discriminative classifier yields a better system, irrespective of whether the spoofed signal is replayed to the microphone or is directly injected into the system software process. Cross-database investigations show that neither the short-term spectral processing based approaches nor the proposed approach yield systems which are able to generalize across databases or methods of attack. Thus, revealing the difficulty of the problem and the need for further resources and research.

show abstract

Section: Analysis Of the Discriminationmentioning

confidence: 99%

Section: Analysis Of the Discriminationmentioning

confidence: 99%

Long-Term Spectral Statistics for Voice Presentation Attack Detection

Muckenhirn

Korshunov

Magimai-Doss

et al. 2017

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…A researcher has proposed Breath-Group Theory which holds that the breath-group is a basic unit of intonation production and perception [1]. Other researcher in their studies believes that an important function of the breathing system is to produce subglottal pressure and then the sound flow [2]. It increases or decreases at the prosodic boundaries.…”

Section: Introductionmentioning

confidence: 99%

A Study on the Rhythm and Respiratory Characteristics of Zhuang Language

Liu¹,

Feng²

2018

Acta sci. Malays.

View full text Add to dashboard Cite

This research studies the features of chest and abdominal breathing in Zhuang language. Two participants were recruited to record 30 news articles of Zhuang language. The chest and abdominal breathing signals as well as speech signal were recorded simultaneously. Programs for breathing analysis have been written to extract parameters such as breathing reset amplitude, time of inhale phase, and slope of exhale phase. The results show that the times of inhale and exhale reset of abdominal breathing are earlier than chest breathing, the breathing reset is related to prosodic boundaries.

show abstract

“…Lieberman (1967) proposed Breath-Group Theory which holds that the breath-group is a basic unit of intonation production and perception. Ohala (1990) believes that an important function of the breathing system is to produce sub-glottal pressure and then the sound flow. It increases or decreases at the prosodic boundaries.…”

Section: Introductionmentioning

confidence: 99%

A Study on the Rhythm and Respiratory Characteristics of Zhuang Language

2018

2018 International Conference on Arts, Linguistics, Literature and Humanities (ICALLH 2018)

View full text Add to dashboard Cite

This paper studies the features of chest and abdominal breathing in Zhuang language. Two participants were recruited to record 30 news of Zhuang language. The chest and abdominal breathing signals as well as speech signal were recorded simultaneously. Programs for breathing analysis have been written to extract parameters such as breathing reset amplitude, time of inhale phase, and slope of exhale phase. The results show that the times of inhale and exhale reset of abdominal breathing are earlier than chest breathing, the breathing reset is related to prosodic boundaries.

show abstract

Respiratory Activity in Speech

Cited by 52 publications

References 45 publications

Long-Term Spectral Statistics for Voice Presentation Attack Detection

Long-Term Spectral Statistics for Voice Presentation Attack Detection

A Study on the Rhythm and Respiratory Characteristics of Zhuang Language

A Study on the Rhythm and Respiratory Characteristics of Zhuang Language

Contact Info

Product

Resources

About