Publication
Implementation of VTLN for Statistical Speech Synthesis
Philip Neil Garner, John David Scott Dines, Hui Liang, Lakshmi Babu Saheer
2010
Report or working paper
2010
Report or working paper
Abstract
Vocal tract length normalization is an important feature normalization technique that can be used to perform speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The EM formulation helps to embed the feature normalization in the HMM training. This helps in estimating the warping factors more efficiently and enables the use of multiple (appropriate) warping factors for different state clusters of the same speaker.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Related concepts (15)
Speaker recognition
Speaker recognition is the identification of a person from characteristics of voices. It is used to answer the question "Who is speaking?" The term voice recognition can refer to speaker recognition or speech recognition. Speaker verification (also called speaker authentication) contrasts with identification, and speaker recognition differs from speaker diarisation (recognizing when the same speaker is speaking).
Speech recognition
Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the computer science, linguistics and computer engineering fields. The reverse process is speech synthesis.
Matrix mechanics
Matrix mechanics is a formulation of quantum mechanics created by Werner Heisenberg, Max Born, and Pascual Jordan in 1925. It was the first conceptually autonomous and logically consistent formulation of quantum mechanics. Its account of quantum jumps supplanted the Bohr model's electron orbits. It did so by interpreting the physical properties of particles as matrices that evolve in time. It is equivalent to the Schrödinger wave formulation of quantum mechanics, as manifest in Dirac's bra–ket notation.
Related publications (32)
Sparse Autoencoders for Speech Modeling and Recognition
Speech recognition-based applications upon the advancements in artificial intelligence play an essential role to transform most aspects of modern life. However, speech recognition in real-life conditions (e.g., in the presence of overlapping speech, varyin ...
EPFL2023Novel Methods For Detection And Analysis Of Atypical Aspects In Speech
Atypical aspects in speech concern speech that deviates from what is commonly considered normal or healthy. In this thesis, we propose novel methods for detection and analysis of these aspects, e.g. to monitor the temporary state of a speaker, diseases tha ...
EPFL2023Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features
Mathew Magimai Doss, Julian David Fritsch
In the literature, the task of dysarthric speech intelligibility assessment has been approached through development of different low-level feature representations, subspace modeling, phone confidence estimation or measurement of automatic speech recognitio ...
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021