Global ETD Search

Towards Natural-Sounding Artificial Polyglot Voices: from Voice Conversion to Text-to-Speech via Generative Speech Modeling

Di Caro, Luigi, Ruggiero, GiuseppeUniversità degli Studi di Torino2026

unito Repository record for Towards Natural-Sounding Artificial Polyglot Voices: from Voice Conversion to Text-to-Speech via Generative Speech Modeling (opens in a new tab)

Speech Representation Models for Speech Synthesis and Multimodal Speech Recognition

Sun, Felix (Felix W.)Massachusetts Institute of Technology2016

The field of speech recognition has seen steady advances over the last two decades, leading to the accurate, real-time recognition systems available on mobile phones today. In this thesis, I apply speech modeling techniques developed for recognition to two other speech problems: speech synthesis …

mit Repository record for Speech Representation Models for Speech Synthesis and Multimodal Speech Recognition (opens in a new tab)

Multimodal Fusion With Applications to Audio -Visual Speech Recognition

Chu, Stephen MingyuUniversity of Illinois at Urbana-Champaign2015

… of the intermodal couplings in audio-visual speech recognition and in multichannel biometrics defy a universal fusion method for both applications. For audio-visual speech modeling, we propose a novel sensory fusion method based on the coupled hidden Markov models (CHMMs). The CHMM framework …

uiuc Repository record for Multimodal Fusion With Applications to Audio -Visual Speech Recognition (opens in a new tab)

Articulatory features for robust visual speech recognition

Saenko, Ekaterina, 1976-Massachusetts Institute of Technology2004

This thesis explores a novel approach to visual speech modeling. Visual speech, or a sequence of images of the speaker's face, is traditionally viewed as a single stream of contiguous units, each corresponding to a phonetic segment. These units are defined heuristically by mapping several visually …

mit Repository record for Articulatory features for robust visual speech recognition (opens in a new tab)

Modeling spontaneous speech variability for large vocabulary continuous speech recognition

Schramm, HaukePublikationsserver der RWTH Aachen University2006

… techniques for improved treatment of spontaneous speech variabilities in large vocabulary automatic speech recognition are developed and evaluated on US English conversational speech and spontaneous medical dictations. Two main aspects of spontaneous speech modeling are addressed: The general …

aachen Repository record for Modeling spontaneous speech variability for large vocabulary continuous speech recognition (opens in a new tab)

Probabilistic generative modeling of speech

Zhang, YangUniversity of Illinois at Urbana-Champaign2016

Speech processing refers to a set of tasks that involve speech analysis and synthesis. Most speech processing algorithms model a subset of speech parameters of interest and blur the rest using signal processing techniques and feature extraction. However, evidence shows that many speech parameters …

uiuc Repository record for Probabilistic generative modeling of speech (opens in a new tab)