Estimating Speaker Height and Subglottal Resonances Using MFCCs and GMMs

Arsikere, Harish; Alwan, Abeer

doi:10.1109/lsp.2013.2295397

Cited by 19 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most certainly, the computer has exceeded human ability of laymen when considering the domain of health state or pathology assessment from the voice and words such as when automatically diagnosing Autism Spectrum Condition [11], Alzheimer's [12] or Parkinson's disease [13]. Other examples exist such as predicting height [14] or heart rate [15] from voice acoustics down to some centimetres or beats per minute, where automatic approaches are likely a nodge ahead, albeit human perception tests for comparison are largely missing. Mostly in the psychological and phonetic literature, some do exist such as for excemptions for human age perception in speech such as [16], [17]) or speaker height such as [?].…”

Section: A Superhuman Yet?mentioning

confidence: 99%

Automatic speaker analysis 2.0: Hearing the bigger picture

Schuller

2017

2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)

View full text Add to dashboard Cite

Automatic Speaker Analysis has largely focused on single aspects of a speaker such as her ID, gender, emotion, personality, or health state. This broadly ignores the interdependency of all the different states and traits impacting on the one single voice production mechanism available to a human speaker. In other words, sometimes we may sound depressed, but we simply have a flu, and hardly find the energy to put more vocal effort into our articulation and sound production. Recently, this lack gave rise to an increasingly holistic speaker analysis -assessing the 'larger picture' in one pass such as by multi-target learning. However, for a robust assessment, this requires large amount of speech and language resources labelled in rich ways to train such interdependency, and architectures able to cope with multi-target learning of massive amounts of speech data. In this light, this contribution will discuss efficient mechanisms such as large socialmedia pre-scanning with dynamic cooperative crowd-sourcing for rapid data collection, cross-task-labelling of these data in a wider range of attributes to reach 'big & rich' speech data, and efficient multi-target end-to-end and end-to-evolution deep learning paradigms to learn an accordingly rich representation of diverse target tasks in efficient ways. The ultimate goal behind is to enable machines to hear the 'entire' person and her condition and whereabouts behind the voice and words -rather than aiming at a single aspect blind to the overall individual and its state, thus leading to the next level of Automatic Speaker Analysis.

show abstract

Section: A Superhuman Yet?mentioning

confidence: 99%

Automatic speaker analysis 2.0: Hearing the bigger picture

Schuller

2017

2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)

View full text Add to dashboard Cite

show abstract

“…Many of these works employ Mel Frequency Cepstral Coefficients (MFCC) to process the recorded sound waves [1,20,24,30,35,40,43,54]. In point of fact, since the mid-eighties MFCC has been the most widely used feature extraction method in the field of ASR [19].…”

Section: Mel Frequency Cepstral Coefficientmentioning

confidence: 99%

Classifying infant cry patterns by the Genetic Selection of a Fuzzy Model

Rosales-Pérez

Reyes-García

González

et al. 2015

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Among various physical characteristics, scientific studies have investigated the correlation between voice characteristics and a speaker's age and height. Authors of [1,2] reported that the vocal tract length, sub-glottal resonance frequencies, and formant frequencies are correlated with the individual's height. Other voice characteristics of speech such as speech rate, sound pressure level, fundamental frequency, etc.…”

Section: Introductionmentioning

confidence: 99%

Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model

Gupta¹,

Truong²,

Anh³

et al. 2022

Preprint

View full text Add to dashboard Cite

The estimation of speaker characteristics such as age and height is a challenging task, having numerous applications in voice forensic analysis. In this work, we propose a bi-encoder transformer mixture model for speaker age and height estimation. Considering the wide differences in male and female voice characteristics such as differences in formant and fundamental frequencies, we propose the use of two separate transformer encoders for the extraction of specific voice features in the male and female gender, using wav2vec 2.0 as a common-level feature extractor. This architecture reduces the interference effects during backpropagation and improves the generalizability of the model. We perform our experiments on the TIMIT dataset and significantly outperform the current state-of-the-art results on age estimation. Specifically, we achieve root mean squared error (RMSE) of 5.54 years and 6.49 years for male and female age estimation, respectively. Further experiment to evaluate the relative importance of different phonetic types for our task demonstrate that vowel sounds are the most distinguishing for age estimation. 1

show abstract

Estimating Speaker Height and Subglottal Resonances Using MFCCs and GMMs

Cited by 19 publications

References 13 publications

Automatic speaker analysis 2.0: Hearing the bigger picture

Automatic speaker analysis 2.0: Hearing the bigger picture

Classifying infant cry patterns by the Genetic Selection of a Fuzzy Model

Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model

Contact Info

Product

Resources

About