Naturalness

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

Bayesian naturalness, simplicity, and testability applied to the $B−L$ MSSM GUT

Abstract: Recent years have seen increased use of Bayesian model comparison to quantify notions such as naturalness, simplicity, and testability, especially in the area of supersymmetric model building. After demonstrating that Bayesian model comparison can resolve a paradox that has been raised in the literature concerning the naturalness of the proton mass, we apply Bayesian model comparison to GUTs, an area to which it has not been applied before. We find that the GUTs are substantially favored over the non-unifying puzzle model. Of the GUTs we consider, the $B-L$ MSSM GUT is the most favored, but the MSSM GUT is almost equally favored.

Beyond the Standard Model theory

Abstract: I discuss the central challenges to fundamental physics raised by the discovery of the Higgs, revolving around ?naturalness? and its discontents

Phonological Reduction in Swedish

Abstract: In this paper, the importance of pronunciation varia- tion modelling is discussed. As a first step in devel- oping a model of Swedish pronunciation variation due to speaking style and speech rate, a tentative reduc- tion rule system has been developed. An assessment experiment testing the impact of phonological reduc- tion, as defined by this system, on the perceived natu- ralness of speech synthesis was conducted. Canonical and reduced synthetic speech stimuli with three differ- ent speech rates were presented to na¨ ive subjects. The reduced pronunciations were significantly more often perceived as more natural than the canonical pronun- ciations at the higher speech rates, while there was no significant general difference in perceived naturalness depending on reduction level for the lowest rate. The dependence on speech rate for perceived naturalness was significant. A possible cause for some observed differences in perceived naturalness depending on the nature of specific stimuli is discussed. For a general description of speaking style dependent pronunciation variation in Swedish, both phonological and phonetic level rules will have to be developed. For this purpose, data-driven methods will be used on an- notated spontaneous speech corpora. The focus will be on general aspects of pronunciation variation, rather than on variation due to dialect or individual factors. As a starting point, a tentative knowledge-based phonological level rule system has been developed. The purpose of this rule system is to form a base from which a more elaborate rule system can be built. The rule system has some empirical grounds, since it is based partly on empirical results reported by Garding (1). The result of applying the rule system to canonical (maximally detailed) transcriptions can be compared to what can be observed in spontaneous speech cor- pora and the rules updated, if systematic deviations are found. The phonological rules can also serve as a skeleton to which more detailed phonetic rules can be added. In this paper, an assessment experiment testing the impact on the perceived naturalness of speech synthesis of the tentative rule system is reported. The specific questions asked are: 1) What is the impact on the perceived naturalness of synthesis output of applying the rule system to the input transcriptions, 2) What is the correlation between the perceived naturalness of the rule-processed stimuli and synthesis speech rate and 3) Are there differences in perceived naturalness depending on the rules applied and, if so, how can these differences be explained? 1.1 BACKGROUND

Problem-Agnostic Speech Embeddings for Multi-Speaker Text-to-Speech with SampleRNN

Abstract: Text-to-speech (TTS) acoustic models map linguistic features into an acoustic representation out of which an audible waveform is generated. The latest and most natural TTS systems build a direct mapping between linguistic and waveform domains, like SampleRNN. This way, possible signal naturalness losses are avoided as intermediate acoustic representations are discarded. Another important dimension of study apart from naturalness is their adaptability to generate voice from new speakers that were unseen during training. In this paper we first propose the use of problem-agnostic speech embeddings in a multi-speaker acoustic model for TTS based on SampleRNN. This way we feed the acoustic model with speaker acoustically dependent representations that enrich the waveform generation more than discrete embeddings unrelated to these factors. Our first results suggest that the proposed embeddings lead to better quality voices than those obtained with discrete embeddings. Furthermore, as we can use any speech segment as an encoded representation during inference, the model is capable to generalize to new speaker identities without retraining the network. We finally show that, with a small increase of speech duration in the embedding extractor, we dramatically reduce the spectral distortion to close the gap towards the target identities.