Essays about: "competitive speech"

Showing result 1 - 5 of 11 essays containing the words competitive speech.

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

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Fredrik Cumlin; [2022]
    Keywords : 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.;

    Abstract : 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). READ MORE

  3. 2. SPEECH SYNTHESIS AND RECOGNITION FOR A LOW-RESOURCE LANGUAGE Connecting TTS and ASR for mutual benefit

    University essay from Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori

    Author : Liliia Makashova; [2021-09-23]
    Keywords : Speech synthesis; automatic speech recognition; low-resource language; machine learning; transfer learning;

    Abstract : Speech synthesis (text-to-speech, TTS) and speech recognition (automatic speech recognition, ASR) are the NLP technologies that are the least available for low-resource and indigenous languages. Lack of computational and data resources is the major obstacle when it comes to the development of linguistic tools for these languages. READ MORE

  4. 3. Instability of a bi-directional TiFGAN in unsupervised speech representation learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Matthaios Stylianidis; [2021]
    Keywords : ;

    Abstract : A major challenge in the application of machine learning in the speech domain is the unavailability of annotated data. Supervised machine learning techniques are highly dependent on the amount of labelled data and the quality of the labels. READ MORE

  5. 4. Gender and Language similarities and differences in mixed sex conversations and same sex conversations in the American TV series Modern Family

    University essay from Högskolan Väst/Avd för utbildningsvetenskap och språk

    Author : Feisal Ali; [2021]
    Keywords : Gender difference; language difference; men’s speech styles; women’s speech styles; same-sex conversations; mixed-sex conversations; cooperative; competitive; and Interruptions;

    Abstract : The study aimed to analyze females and males in mixed-sex conversations and same-sex conversations using cooperative speech, competitive speech, interruptions, and similarities and differences in their communication styles in the Tv series modern family. Men and women are said to use different speech styles regarding cooperative, competitive, and interruptions. READ MORE

  6. 5. Normalizing Flow based Hidden Markov Models for Phone Recognition

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Anubhab Ghosh; [2020]
    Keywords : Phone recognition; generative learning; Normalizing flows; Decision fusion; Speech recognition;

    Abstract : The task of Phone recognition is a fundamental task in Speech recognition and often serves a critical role in bench-marking purposes. Researchers have used a variety of models used in the past to address this task, using both generative and discriminative learning approaches. READ MORE