Voice conversion using deep bidirectional long short-term memory based recurrent neural networks
This paper investigates the use of Deep Bidirectional Long Short-Term Memory based
Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal correlations …
Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal correlations …
Phone-aware LSTM-RNN for voice conversion
This paper investigates a new voice conversion technique using phone-aware Long Short-
Term Memory Recurrent Neural Networks (LSTM-RNNs). Most existing voice conversion …
Term Memory Recurrent Neural Networks (LSTM-RNNs). Most existing voice conversion …
Voice conversion of tagalog synthesized speech using cycle-generative adversarial networks (cycle-gan)
JB Ganhinhin, MDB Varona… - 2022 IEEE 12th …, 2022 - ieeexplore.ieee.org
Existing Tagalog Text-to-speech (TTS) systems still have room for improvement, and
although recent attempts at creating local TTS systems for Philippine spoken languages …
although recent attempts at creating local TTS systems for Philippine spoken languages …
An automatic voice conversion evaluation strategy based on perceptual background noise distortion and speaker similarity
Voice conversion aims to modify the characteristics of one speaker to make it sound like
spoken by another speaker without changing the language content. This task has attracted …
spoken by another speaker without changing the language content. This task has attracted …
Comparative Analysis of Direct Speech-to-Speech Translation and Voice Conversion Using Bi-LSTM
L Arya, SNVG Bhamidi, S Prabha… - … 26th Conference of …, 2023 - ieeexplore.ieee.org
This study aims to conduct a comparative analysis between Direct Speech to Speech
Translation (DS2ST) and Voice Conversion (VC) utilizing a Bi-Directional Long Short-Term …
Translation (DS2ST) and Voice Conversion (VC) utilizing a Bi-Directional Long Short-Term …
Techniques for spectral voice conversion
V Popa - 2012 - trepo.tuni.fi
Voice conversion is a speech technology encompassing transformations applied to the
speech signal with the purpose of changing the perceived speaker identity from a source …
speech signal with the purpose of changing the perceived speaker identity from a source …
[PDF][PDF] Wawasimi: Clasificación de nivel de desarrollo de lenguaje e identificación de procesos fonológicos en niños de 3 a 5 años
BS Baldeón Albornoz, RA Ravelli Altamirano - repositorioacademico.upc.edu.pe
Los trastornos del lenguaje y habla dificultan el desarrollo de los niños en diferentes
aspectos: educativos, sociales, emocionales, entre otros. Estas dificultades empeoran y son …
aspectos: educativos, sociales, emocionales, entre otros. Estas dificultades empeoran y son …
[引用][C] Voice conversion for dubbing using linear predictive coding and hidden markov model
FM Mukhneri, I Wijayanto, S Hadiyoso - Journal of Southwest Jiaotong University, 2020
A Parametric Approach for Efficient Speech Storage, Flexible Synthesis and Voice Conversion
J Nurminen - 2013 - trepo.tuni.fi
During the past decades, many areas of speech processing have benefited from the vast
increases in the available memory sizes and processing power. For example, speech …
increases in the available memory sizes and processing power. For example, speech …