Hierarchical stress generation with Fujisaki model in expressive speech synthesis

Li, Ya; Tao, Jianhua; Hirose, Keikichi; Lai, Wei Kuang; Xu, Xiaoying

doi:10.21437/speechprosody.2014-196

Cited by 15 publications

(17 citation statements)

References 19 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speech Analyses Because origin (e.g., Ordin & Mennen, 2017;Zimmerer et al, 2014) and language (e.g., Andreeva et al, 2014;Keating & Kuo, 2012;Traunmüller & Eriksson, 1995) influence speech characteristics and vocal quality parameters, we only analyzed participants who were native French speakers with European ascendants. We also only focused on participants who declared themselves as homosexual and heterosexual (we excluded those who declared to be bisexual or other).…”

Section: Speech Samples and Acoustic Analysis Proceduresmentioning

confidence: 99%

Speech Acoustic Features: A Comparison of Gay Men, Heterosexual Men, and Heterosexual Women

et al. 2020

View full text Add to dashboard Cite

Potential differences between homosexual and heterosexual men have been studied on a diverse set of social and biological traits. Regarding acoustic features of speech, researchers have hypothesized a feminization of such characteristics in homosexual men, but previous investigations have so far produced mixed results. Moreover, most studies have been conducted with English-speaking populations, which calls for further cross-linguistic examinations. Lastly, no studies investigated so far the potential role of testosterone in the association between sexual orientation and speech acoustic features. To fill these gaps, we explored potential differences in acoustic features of speech between homosexual and heterosexual native French men and investigated whether the former showed a trend toward feminization by comparing theirs to that of heterosexual native French women. Lastly, we examined whether testosterone levels mediated the association between speech acoustic features and sexual orientation. We studied four sexually dimorphic acoustic features relevant for the qualification of feminine versus masculine voices: the fundamental frequency, its modulation, and two understudied acoustic features of speech, the harmonics-to-noise ratio (a proxy of vocal breathiness) and the jitter (a proxy of vocal roughness). Results showed that homosexual men displayed significantly higher pitch modulation patterns and less breathy voices compared to heterosexual men, with values shifted toward those of heterosexual women. Lastly, testosterone levels did not influence any of the investigated acoustic features. Combined with the literature conducted in other languages, our findings bring new support for the feminization hypothesis and suggest that the feminization of some acoustic features could be shared across languages.

show abstract

Section: Speech Samples and Acoustic Analysis Proceduresmentioning

confidence: 99%

Speech Acoustic Features: A Comparison of Gay Men, Heterosexual Men, and Heterosexual Women

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In read speech, BrE and IndE hardly differ in pitch dynamism as measured by PDQ. Both have higher PDQ scores than French and German speakers [11]. By contrast, in spontaneous speech, PDQ is higher for IndE than for BrE, indicating a wider pitch range.…”

Section: Dicussionmentioning

confidence: 76%

“…Such attitudinal evaluations may be acutely felt by language learners, who, as a range of studies has shown, tend to have a compressed pitch range compared to native speakers [3,[10][11][12]. This result has also been confirmed for speakers learning English as a foreign language, such as L1 Swedish or L1 Italian learners of English, who use English mainly for international communication [13,14].…”

Section: Introductionmentioning

confidence: 94%

Pitch Range, Dynamism and Level in Postcolonial Varieties of English: A Comparison of Educated Indian English and British English

Fuchs

2018

Speech Prosody 2018

View full text Add to dashboard Cite

Pitch range (difference between maximum and minimum pitch), pitch dynamism and mean pitch level have been shown to differ between varieties of English, and such differences can lead to (un)favourable judgements about a speaker's attitude and likeability. Little is known about pitch range in nativised varieties of English, which are spoken in postcolonial countries. While in many functional and structural ways they are similar to native varieties, in other ways they resemble learner varieties. Since learners commonly have a compressed pitch range compared to native speakers, this paper investigates pitch range and level in 20 speakers of Educated Indian English (IndE) in order to determine whether IndE is similar to British English or more like learner varieties in this respect. The analysis reveals that IndE has a smaller pitch range than British English in read speech, but a wider pitch range in spontaneous speech, which is not compatible with results for learner varieties. Moreover, IndE has a higher pitch level than BrE. These prosodic differences might explain reports of crosscultural communication difficulties. Finally, the comparison of four different L1 backgrounds in IndE also shows small L1based differences, which, however, are not significant.

show abstract

“…As final rises (H%) are used in French and German to signal interrogativity, German learners might tend to generalize the H% pattern (and the marker ECQ) for all types of questions -in spite of the pragmatic differences between and the alluded intonational variability in both languages (see studies on interrogatives and their prosody in L2: [21], [22], [23] Earlier research on L2 intonation has shown that learner data are characterized by a narrower pitch range and a lower degree of F0 variability (see [24] for L2 French read data produced by German learners). The same holds true for speech rate: L2 speech is known to be typically slower than L1 speech ( [25]).…”

Section: Aims and Hypothesesmentioning

confidence: 99%

“…SD/mean), based on manually corrected files (exclusion of octave jumps and wrong measurements). In accordance with the method applied by [24], we used time steps of 0.01s for male and of 0.005s for female subjects. We furthermore determined the speech rate (in syllables per second) for each utterance.…”

Section: Parameters Analyzedmentioning

confidence: 99%

Intonation and (re)syllabification in L2 French interrogatives produced by L1 German learners: Comparing different proficiency levels

Gabriel¹,

Meisenburg²,

Wocker³

2018

Speech Prosody 2018

View full text Add to dashboard Cite

The study investigates the prosody of French interrogatives produced by L1 German learners of three different proficiency levels. Control data from French native speakers are taken into account. The materials analyzed were recorded using two different versions of a Discourse Completion Task (DCT) for the advanced learners and the native controls and a scripted version thereof in the form of a screenplay for the beginners. It is shown that despite the general difference between the intonation systems of (phrase-based) French and (word-based) German the learners mostly produce well identifiable interrogative contours, and their data do not differ significantly from the native control data regarding the use of F0, measured in terms of pitch range and variability (Pitch Dynamism Quotient, PDQ). However, the learners differ significantly from the native speakers in presenting a lower speech rate and in their way of (re)syllabifying their utterances: they produce less target-like instances of liaison and enchaînement and more word-initial glottalizations. This suggests that, at least for short speech acts such as we analyzed, the learners' challenge to produce the prosody of French interrogatives in a target-like way rather refers to the syllabic than to the intonational level.

show abstract

Hierarchical stress generation with Fujisaki model in expressive speech synthesis

Cited by 15 publications

References 19 publications

Speech Acoustic Features: A Comparison of Gay Men, Heterosexual Men, and Heterosexual Women

Speech Acoustic Features: A Comparison of Gay Men, Heterosexual Men, and Heterosexual Women

Pitch Range, Dynamism and Level in Postcolonial Varieties of English: A Comparison of Educated Indian English and British English

Intonation and (re)syllabification in L2 French interrogatives produced by L1 German learners: Comparing different proficiency levels

Contact Info

Product

Resources

About