Speech feature extraction using linear Chirplet transform and its applications*

Duc, Hao; Chau, Duc Thanh; Son, Tran Hung

doi:10.1080/24751839.2023.2207267

Cited by 3 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These coefficients can be obtained by solving a system of linear equations using methods such as autocorrelation, covariance. The second step in LPC analysis is to remove the effect of the LPC coefficients from the speech signal [36]. This can be done by filtering the speech signal with the inverse of the LPC filter, which is also called the prediction error filter.…”

Section: Source-filter Approachmentioning

confidence: 99%

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

NAVEENKUMAR

2024

Preprint

View full text Add to dashboard Cite

In this research, it is suggested that a hybrid architecture for text-to-speech, which is named it as Efficient Speech Synthesizer. ESS optimizes all the parameters through a consistent, end-to-end training process that enables fast and efficient speech synthesis of exceptional quality without depending on the length of the sentences. ESS is powered by combining feed-forward approaches like Variational Auto Encoders and Linear Predictive Coding techniques. These techniques give monotonic limitations to the sequence alignment with almost no increase in computation. The present research focuses on TTS model with low complexity, low latency which is suitable for both high-end and low-end computational devices like IoT and smart Phones.

show abstract

Section: Source-filter Approachmentioning

confidence: 99%

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

NAVEENKUMAR

2024

Preprint

View full text Add to dashboard Cite

show abstract

Speech Enhancement Using Dynamical Variational AutoEncoder

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Exploiting auditory filter models as interpretable convolutional frontends to obtain optimal architectures for speaker gender recognition

Fayyazi,

Shekofteh

2023

Applied Acoustics

View full text Add to dashboard Cite

Speech feature extraction using linear Chirplet transform and its applications*

Cited by 3 publications

References 18 publications

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

Speech Enhancement Using Dynamical Variational AutoEncoder

Exploiting auditory filter models as interpretable convolutional frontends to obtain optimal architectures for speaker gender recognition

Contact Info

Product

Resources

About

Speech feature extraction using linear Chirplet transform and its applications*

Cited by 3 publications

References 18 publications

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE &amp; LPC-net with independent sentence length

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE &amp; LPC-net with independent sentence length

Speech Enhancement Using Dynamical Variational AutoEncoder

Exploiting auditory filter models as interpretable convolutional frontends to obtain optimal architectures for speaker gender recognition

Contact Info

Product

Resources

About

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length

An Efficient Speech Synthesizer – A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length