Naturalness

About: Naturalness is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 31737 citations.

Data Selection and Adaptation for Naturalness in HMM-Based Speech Synthesis.

Abstract: We describe experiments in building HMM text-to-speech voices on professional broadcast news data from multiple speakers. We build on earlier work comparing techniques for selecting utterances from the corpus and voice adaptation to produce the most natural-sounding voices. While our ultimate goal is to develop intelligible and natural-sounding synthetic voices in low-resource languages rapidly and without the expense of collecting and annotating data specifically for text-to-speech, we focus on English initially, in order to develop and evaluate our methods. We evaluate our approaches using crowdsourced listening tests for naturalness. We have found that removing utterances that are outliers with respect to hyper-articulation, as well as combining the selection of hypoarticulated utterances and low mean f0 utterances, produce the most natural-sounding voices.

Naturalness as a safe haven: parental consumption practices and the management of risk

Abstract: Purpose This paper aims to present an analysis of the various dimensions of naturalness that shape the consumption practices of parents with young children Design/methodology/approach The study builds on semi-structured interviews with 17 mothers and fathers focusing on parental decision-making in everyday consumption from pregnancy to the first years of the child’s life Findings Naturalness is a tool allowing parents to navigate in a world of risks and part of an everyday consumption practice that constructs and maintains children as vulnerable and parents as responsible Parents perceive naturalness as something with three dimensions: familiarity, purity and culture These three dimensions lead to different parental practices around consumption Originality/value The analysis contributes to the authors’ understanding of parenting, childhood, risk, safety and consumption by showing how and why parents of young children construct naturalness as a three-dimensional ideal in their consumption practices

Two Notions of Naturalness

Abstract: My aim in this paper is twofold: (i) to distinguish two notions of naturalness employed in BSM physics and (ii) to argue that recognizing this distinction has methodological consequences. One notion of naturalness is an "autonomy of scales" requirement: it prohibits sensitive dependence of an effective field theory's low-energy observables on precise specification of the theory's description of cutoff-scale physics. I will argue that considerations from the general structure of effective field theory provide justification for the role this notion of naturalness has played in BSM model construction. A second, distinct notion construes naturalness as a statistical principle requiring that the values of the parameters in an effective field theory be "likely" given some appropriately chosen measure on some appropriately circumscribed space of models. I argue that these two notions are historically and conceptually related but are motivated by distinct theoretical considerations and admit of distinct kinds of solution.

Voice source modelling techniques for statistical parametric speech synthesis

Abstract: Speech is the most natural way of human communication, and thus designing a machine that imitates human speech has long fascinated people. Only rather recently, due to digitisation of speech and increase in computing power, this goal has become feasible. Although speech synthesis is used today in various applications from human-computer interaction to assistive technologies, the performance of modern speech synthesisers is far from the abilities of human speakers. The ultimate goal of text-to-speech (TTS) synthesis is to read any text and convert it to intelligible and natural sounding speech with the desired contextual and speaker characteristics. Meeting all of these goals at once makes this task extremely difficult. Moreover, the quality of the speech signal cannot be compromised since humans are very sensitive in perceiving even the slightest artefacts in a speech signal. This thesis aims to improve both the naturalness and expressivity of speech synthesis by developing speech processing algorithms that utilise information from the speech production mechanism. One of the key algorithms in this work is glottal inverse filtering (GIF), which is used for estimating the voice source signal from recorded speech. The voice source is known to be the origin of several essential acoustic cues used in spoken communication, such as the fundamental frequency, but it is also related to acoustic cues underlying voice quality, speaking style, and speaker identity, all of which contribute to the naturalness and expressivity of speech. Accurate modelling of the voice source is often overlooked in conventional speech processing algorithms, and this work aims to improve especially this shortcoming. In this thesis, two new GIF methods are first proposed that can be used for improved estimation of the voice source signal. Secondly, several novel voice source parameterization and modelling methods are developed that can be used in statistical parametric speech synthesis (SPSS) to improve naturalness and expressivity. Thirdly, using GIF and the voice source modelling methods in the context of SPSS, expressive voices are created that aim to cover various human speaking styles used in everyday spoken communication. Finally, the created synthetic voices are assessed using extensive subjective evaluation in different listening conditions. The results of the evaluation show that the naturalness and expressivity of synthetic speech can be enhanced using the techniques proposed in this thesis, and that the voices are perceived to be more suitable in various realistic contexts. Thus, the methods presented in this thesis provide a large potential to enhance the naturalness, expressivity, and suitability of speech synthesis in various applications.; Puhe on ihmisten luonnollisin tapa kommunikoida, ja siksi puhetta tuottavan koneen suunnittelu on jo kauan kiehtonut ihmisia. Kuitenkin vasta viime vuosikymmenina puhesynteesista on tullut kaytannossa mahdollista, mika suureksi osaksi on johtunut puheen digitaalisesta esitysmuodosta ja kasvaneesta…

Solving the Naturalness Problem by Baby Universes in the Lorentzian Multiverse

Abstract: We propose a solution of the naturalness problem in the context of the multiverse wavefunction without the anthropic argument. If we include microscopic wormhole configurations in the path integral, the wave function becomes a superposition of universes with various values of the coupling constants such as the cosmological constant, the parameters in the Higgs potential, and so on. We analyze the quantum state of the multiverse, and evaluate the density matrix of one universe. We show that the coupling constants induced by the wormholes are fixed in such a way that the density matrix is maximized. In particular, the cosmological constant, which is in general time-dependent, is chosen such that it takes an extremely small value in the far future. We also discuss the gauge hierarchy problem and the strong CP problem in this context. Our study predicts that the Higgs mass is 140\pm20 GeV and {\theta}=0.