Sökning: "Speech naturalness"

Visar resultat 1 - 5 av 11 uppsatser innehållade orden Speech naturalness.

1. 1. Gradually Changing Gender Attribution of Speech Recordings Using Interpolated Filters

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Mira Kjellin; [2022]
   Nyckelord :Mathematics and Statistics;

   Sammanfattning : When we listen to human speech, one of the first characteristics we assess is the gender of the speaker. For individuals who suffer from gender dysphoria, this may cause them to be negatively impacted by their voice not matching their gender identity. Therefore, some persons attempt to change their voices with a speech-language therapist. LÄS MER

3. 2. LaMOSNet: Latent Mean-Opinion-Score Network for Non-intrusive Speech Quality Assessment : Deep Neural Network for MOS Prediction

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Fredrik Cumlin; [2022]
   Nyckelord :Speech naturalness assessment; Speech quality assessment; Mean opinion score; Voice conversion challenge; Semi-supervised learning; Noisy labels.; Naturligt tal bedömning; Ljudkvalitetsbedömning; Medel bedömningsvärdet; Talkonverteringsutmaningen; Semi-övervakad inlärning; Varierande märkningar.;

   Sammanfattning : Objective non-intrusive speech quality assessment aimed to emulate and correlate with human judgement has received more attention over the years. It is a difficult problem due to three reasons: data scarcity, noisy human judgement, and a potential uneven distribution of bias of mean opinion scores (MOS). LÄS MER

4. 3. Research in methods for achieving secure voice anonymization : Evaluation and improvement of voice anonymization techniques for whistleblowing

   Uppsats för yrkesexamina på avancerad nivå, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Erik Hellman; Mattias Nordstrand; [2022]
   Nyckelord :Voice anonymization; voice deanonymization; data privacy; machine learning; neural networks; whistleblowing; röstanonymisering; röstdeanonymisering; datasäkerhet; maskininlärning; neurala nätverk; visselblåsning;

   Sammanfattning : Safe whistleblowing within companies could give a more transparent and open society, and keeping the whistleblower safe is key, this has led to a new EU Whistleblowing Directive requiring each organization with more than 249 employees to provide an internal channel for whistleblowing before 17 July 2022. A whistleblowing service within an entity should provide secure communication for the organization and its employees. LÄS MER

5. 4. A speech therapy support tool based on spectral density adjustment

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Erik Stålberg; Artur Lidström; [2021]
   Nyckelord :speech therapy; spectral estimation; fundamental frequency estimation; FIR filter design; Mathematics and Statistics; Medicine and Health Sciences;

   Sammanfattning : The purpose of this work is to expand the toolbox of speech language pathologists and give them the ability to redesign a patient’s voice to a healthier sounding one, thereby giving the patient a target voice to strive towards. A modified voice is generated by applying a finite impulse response (FIR) filter, altering the spectrum of the patient’s voice. LÄS MER

7. 5. Generative Adversarial Networks for Cross-Lingual Voice Conversion

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Fredrik Ankaräng; [2021]
   Nyckelord :Generative Adversarial Network; CycleGAN; Cross-Lingual Voice Conversion; Speech Synthesis; Machine Learning;

   Sammanfattning : Speech synthesis is a technology that increasingly influences our daily lives, in the form of smart assistants, advanced translation systems and similar applications. In this thesis, the phenomenon of making one’s voice sound like the voice of someone else is explored. LÄS MER