Speaker verification in real-world applications sometimes deals with limited duration of enrollment and/or test data. MFCC-based i-vector systems have defined the state-of-the-art for speaker verification, but it is well known that they are less effective with short utterances. To address this issue, we propose a method to leverage the speaker specificity and stationarity of subglottal acoustic...

In this study, we propose a new method of adapting language models for speech recognition using para-linguistic and extralinguistic features in speech. When we talk with others, we often change the way of lexical choice and speaking style according to various contextual factors. This fact indicates that the performance of automatic speech recognition can be improved by taking the contextual fac...

Speech under face cover constitute a case that is increasingly met by forensic speech experts. Wearing face cover mostly happens when an individual strives to conceal his or her identity. Based on the material of face cover and the level of contact with speech production organs, speech production becomes affected by face mask and a part of speech energy gets absorbed in the mask. There has been...

The human ability to understand speech is underpinned by a hierarchical auditory system whose successive stages process increasingly complex attributes of the acoustic input. It has been suggested that to produce categorical speech perception, this system must elicit consistent neural responses to speech tokens (e.g., phonemes) despite variations in their acoustics. Here, using electroencephalo...

Previous studies showed that both amplitude [1, 6] and phase [4] of the Modulation Spectrum (MS) of speech waveforms play an important role in preserving intelligibility in stress-timed languages like English. In the current study, association between MS and speech intelligibility of spoken sentences in Mandarin and Cantonese which are typical syllable-timed languages [7, 8], is investigated. T...

Automatic glottal inverse filtering with the Markov chain Monte Carlo method Harri Auvinen a, Tuomo Raitio b,∗, Manu Airaksinen b, Samuli Siltanen a, Brad H. Story c, Paavo Alku b a Department of Mathematics and Statistics, University of Helsinki, Helsinki, Finland b Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland c Department of Speech and Hearing Sciences, Univ...

M. Fleischer, S. Kürbis , A. Mainka, P. Birkholz , D. Mürbe Division of Phoniatrics and Audiology, Department of Otorhinolaryngology, Faculty of Medicine Carl Gustav Carus, Technische Universität Dresden, Germany Institute of Acoustics and Speech Communication, Faculty of Electrical and Computer Engineering, Technische Universität Dresden, Germany Voice Research Laboratory, Hochschule für Musik...

Guillaume Barbier, Pascal Perrier, Lucie Ménard, Mark Tiede, Joseph Perkell. Token-to-token variability and anticipatory coarticulation as indicators of maturity of speech motor control in 4-year-old children. 21st International Congress on Acoustics (ICA 2013) 165th Meeting of the Acoustical Society of America, Jun 2013, Montréal, Canada. Acoustical Society of America, Vol. 19, Paper 2aSC22, 2...