Linear transformation approach to VTLN using dynamic frequency warping

Sanand, D. Rama; Kumar, Divyesh; Umesh, S.

doi:10.21437/interspeech.2007-371

Cited by 5 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cox (16) has shown that vocal tract length normalization (VTLN) can be implemented with filter banks and directly applied this method in the feature domain. Later in (17), a linear transformation approach using Dynamic Frequency Warping (DFW) has been proposed for normalization.…”

Section: Introductionmentioning

confidence: 99%

A Bayesian Approach to Estimation of Speaker Normalization Parameters

Ram,

Kundu,

Hegde

2016

Preprint

View full text Add to dashboard Cite

In this work, a Bayesian approach to speaker normalization is proposed to compensate for the degradation in performance of a speaker independent speech recognition system. The speaker normalization method proposed herein uses the technique of vocal tract length normalization (VTLN). The VTLN parameters are estimated using a novel Bayesian approach which utilizes the Gibbs sampler, a special type of Markov Chain Monte Carlo method. Additionally the hyperparameters are estimated using maximum likelihood approach. This model is used assuming that human vocal tract can be modeled as a tube of uniform cross section. It captures the variation in length of the vocal tract of different speakers more effectively, than the linear model used in literature. The work has also investigated different methods like minimization of Mean Square Error (MSE) and Mean Absolute Error (MAE) for the estimation of VTLN parameters. Both single pass and two pass approaches are then used to build a VTLN based speech recognizer. Experimental results on recognition of vowels and Hindi phrases from a medium vocabulary indicate that the Bayesian method improves the performance by a considerable margin.

show abstract

Section: Introductionmentioning

confidence: 99%

A Bayesian Approach to Estimation of Speaker Normalization Parameters

Ram,

Kundu,

Hegde

2016

Preprint

View full text Add to dashboard Cite

show abstract

Studies on inter-speaker variability in speech and its application in automatic speech recognition

Umesh

2011

Sadhana

View full text Add to dashboard Cite

In this paper, we give an overview of the problem of inter-speaker variability and its study in many diverse areas of speech signal processing. We first give an overview of vowel-normalization studies that minimize variations in the acoustic representation of vowel realizations by different speakers. We then describe the universal-warping approach to speaker normalization which unifies many of the vowel normalization approaches and also shows the relation between speech production, perception and auditory processing. We then address the problem of inter-speaker variability in automatic speech recognition (ASR) and describe techniques that are used to reduce these effects and thereby improve the performance of speaker-independent ASR systems.

show abstract

Auditory Representation Effective for Estimating Vocal Tract Information

Irino,

Doan

2023

2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

View full text Add to dashboard Cite

Linear transformation approach to VTLN using dynamic frequency warping

Cited by 5 publications

References 3 publications

A Bayesian Approach to Estimation of Speaker Normalization Parameters

A Bayesian Approach to Estimation of Speaker Normalization Parameters

Studies on inter-speaker variability in speech and its application in automatic speech recognition

Auditory Representation Effective for Estimating Vocal Tract Information

Contact Info

Product

Resources

About