Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 43 for “"voice conversion"”.

  1. Voice Conversion

    … STRAIGHT, ktorý bol dominantne používaný vo Voice Conversion Challenge 2016. Náš system pre konverziu hlasu je založený na konverzii spectra použitím doprednej neurónovej siete a paralelného trénovania.

    brno-tech Repository record for Voice Conversion (opens in a new tab)

  2. CROSS-LINGUAL VOICE CONVERSION

    The thesis focuses on the cross-lingual voice conversion (XVC) that aims to modify a source speaker identity towards a target while preserving the source linguistic content. Firstly, we study the use of bilingual information in XVC including the bilingual linguistic representation and average …

    nus Repository record for CROSS-LINGUAL VOICE CONVERSION (opens in a new tab) Download file for CROSS-LINGUAL VOICE CONVERSION (opens in a new tab)

  3. Noise-Robust Voice Conversion

    … complement to post-processing speech signals is voice conversion, in which speech by one person (source speaker) is made to sound as if spoken by a different person (target speaker). Traditionally, the majority of speech enhancement and voice conversion methods rely on parametric modeling of …

    bucknell Repository record for Noise-Robust Voice Conversion (opens in a new tab)

  4. Non-Parallel Voice Conversion

    Cílem konverze hlasu (voice conversion, VC) je převést hlas zdrojového řečníka na hlas cílového řečníka. Technika je populární je u vtipných internetových videí, ale má také řadu seriózních využití, jako je dabování audiovizuálního materiálu a anonymizace hlasu (například pro ochranu svědků). …

    brno-tech Repository record for Non-Parallel Voice Conversion (opens in a new tab)

  5. MACHINE LEARNING FOR LIMITED DATA VOICE CONVERSION

    Voice Conversion aims to convert one’s voice to sound like that of another. This thesis is focused on developing advanced machine learning algorithms and frameworks for voice conversion under the constraint of limited training data. Firstly, a new voice conversion approach is proposed to address …

    nus Repository record for MACHINE LEARNING FOR LIMITED DATA VOICE CONVERSION (opens in a new tab) Download file for MACHINE LEARNING FOR LIMITED DATA VOICE CONVERSION (opens in a new tab)

  6. Disentanglement Learning for Text-Free Voice Conversion

    Voice conversion (VC) aims to change the perceived speaker identity of a speech signal from one to another, while preserving the linguistic content. Recent state-of-the-art VC systems typically are dependent on automatic speech recognition (ASR) models and they have gained great successes. Results …

    whiterose Download PDF for Disentanglement Learning for Text-Free Voice Conversion (opens in a new tab)

  7. Developing Sparse Representations for Anchor-Based Voice Conversion

    Voice conversion is the task of transforming speech from one speaker to sound as if it was produced by another speaker, changing the identity while retaining the linguistic content. There are many methods for performing voice conversion, but oftentimes these methods have onerous training …

    tamu Repository record for Developing Sparse Representations for Anchor-Based Voice Conversion (opens in a new tab)

  8. Efficient Approaches for Voice Change and Voice Conversion Systems

    In this thesis, the study and design of Voice Change and Voice Conversion systems are presented. Particularly, a voice change system manipulates a speaker’s voice to be perceived as it is not spoken by this speaker; and voice conversion system modifies a speaker’s voice, such that it is perceived …

    maynooth Download PDF for Efficient Approaches for Voice Change and Voice Conversion Systems (opens in a new tab)

  9. SpeechSplit2: An efficient unsupervised speech disentanglement model for multi-aspect voice conversion

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-12-01

    uiuc Repository record for SpeechSplit2: An efficient unsupervised speech disentanglement model for multi-aspect voice conversion (opens in a new tab)

  10. Discussion On Effective Restoration Of Oral Speech Using Voice Conversion Techniques Based On Gaussian Mixture Modeling

    … are useful, they only allow for few default voice selections that do not represent that of the user. In order to achieve total restoration, voice conversion must be introduced. Voice conversion is a method that adjusts a source voice to sound like a target voice. Voice conversion consists of …

    ucf Repository record for Discussion On Effective Restoration Of Oral Speech Using Voice Conversion Techniques Based On Gaussian Mixture Modeling (opens in a new tab)

  11. Técnicas para conversão de orador em sinais de voz

    Presents a voice conversion system, a system that transforms a voice signal spoken by some speaker into a signal that sounds like it was spoken by another speaker, without changing the textual content of the speech or changing information like emotion or emphasis. The main objective of this work is …

    brazil-uerj Repository record for Técnicas para conversão de orador em sinais de voz (opens in a new tab)

  12. EXPRESSIVE SPEECH SYNTHESIS

    … expressiveness. Traditional text-to-speech and voice conversion systems address audio quality independently from visual constraints, while prosodic expressiveness remains an open challenge for emerging visual-aware speech synthesis. This thesis presents four progressive contributions: (1) …

    nus Repository record for EXPRESSIVE SPEECH SYNTHESIS (opens in a new tab) Download file for EXPRESSIVE SPEECH SYNTHESIS (opens in a new tab)

  13. Deep generative models for speech editing

    … as speech synthesis, speech enhancement, and voice conversion. There are two ways that the generative models can help in naturalness for speech processing. The first way is to regularize the speech editing process by defining the sample space of natural speech, and the second way is by …

    uiuc Repository record for Deep generative models for speech editing (opens in a new tab)

  14. Deepfake detection and low-resource language speech recognition using deep learning

    … attack involves using either a text-to-speech voice conversion application to generate audio that mimic the identity of a target speaker. These methods are evaluated on the ASVSpoof 2019 Logical Access dataset containing audio generated using various methods of voice conversion and …

    rit Repository record for Deepfake detection and low-resource language speech recognition using deep learning (opens in a new tab)

  15. Konverze hlasu

    … na cílového. V práci je nejdříve popsána Voice Conversion Challenge (VCC), ve které se účastníci snažili vytvořit co nejlepší systém pro konverzi hlasu. V další části jsou analyzovány komponenty baseline systému použitého ve VCC. Poté jsou navrženy úpravy, které mohou zlepšit kvalitu …

    brno-tech Repository record for Konverze hlasu (opens in a new tab)

  16. Diferenční detekce deepfake reči

    … s využitím technologie konverze hlasu (voice conversion), čímž nabízí zcela nový způsob obrany proti hrozbě deepfake zločinů.

    brno-tech Repository record for Diferenční detekce deepfake reči (opens in a new tab)

  17. Spoofing countermeasures for secure and robust voice authentication system: Feature extraction and modelling

    … noise conditions, by proposing a self-adaptive voice activity detector, which combines cepstral modelling and smoothed energy with the effective post processing stages. Thus, the overarching goal of this thesis is to significantly advance the state-of-the-art in automatic speaker verification …

    unsw Repository record for Spoofing countermeasures for secure and robust voice authentication system: Feature extraction and modelling (opens in a new tab)

  18. THE USE OF REGRESSION MODELS FOR DETECTING DIGITAL FINGERPRINTS IN SYNTHETIC AUDIO

    Modern advancements in text to speech and voice conversion techniques make it increasingly difficult to distinguish an authentic voice from a synthetically generated voice. These techniques, though complex, are relatively easy to use, even for non-technical users. It is important to develop …

    nps Repository record for THE USE OF REGRESSION MODELS FOR DETECTING DIGITAL FINGERPRINTS IN SYNTHETIC AUDIO (opens in a new tab)

Page 1 of 3