A large-scale comparison of two voice synthesis techniques on intelligibility, naturalness, preferences, and attitudes toward voices banked by individuals with amyotrophic lateral sclerosis.

Amyotrophic lateral sclerosis (ALS) commonly results in the inability to produce natural speech, making speech-generating devices (SGDs) important. Historically, synthetic voices generated by SGDs were neither unique, nor age- or dialect-appropriate, which depersonalized SGD use. Voices generated by SGDs can now be customized via voice banking and should ideally sound uniquely like the individual's natural speech, be intelligible, and elicit positive reactions from communication partners. This large-scale 2 x 2 mixed between- and within-participants design examined perceptions of 831 adult listeners regarding custom synthetic voices created for two individuals diagnosed with ALS via two synthesis systems in common clinical use (waveform concatenation and statistical parametric synthesis). The study explored relationships among synthesis system, dysarthria severity, synthetic speech intelligibility, naturalness, and preferences, and also provided a preliminary examination of attitudes regarding the custom synthetic voices. Synthetic voices generated via statistical parametric synthesis trained on deep neural networks were more intelligible, natural, and preferred than voices produced via waveform concatenation, and were associated with more positive attitudes. The custom synthetic voice created from moderately dysarthric speech was more intelligible than the voice created from mildly dysarthric speech. Clinical implications and factors that may have contributed to the relative intelligibilities are discussed.

Voice banking to support individuals who use speech-generating devices: development and evaluation of Singaporean-accented English synthetic voices and a Singapore Colloquial English recording inventory.

Voice banking involves recording an inventory of sentences produced via natural speech. The recordings are used to create a synthetic text-to-speech voice that can be installed on speech-generating devices. This study highlights a minimally researched, clinically relevant issue surrounding the development and evaluation of Singaporean-accented English synthetic voices that were created using readily available voice banking software and hardware. Processes used to create seven unique synthetic voices that produce Singaporean-accented English, and the development of a custom Singaporean Colloquial English (SCE) recording inventory, are reviewed. The perspectives of adults who spoke SCE and banked their voices for this project are summarized and were generally positive. Finally, 100 adults familiar with SCE participated in an experiment that evaluated the intelligibility and naturalness of the Singaporean-accented synthetic voices, as well as the effect of the SCE custom inventory on listener preferences. The addition of the custom SCE inventory did not affect intelligibility or naturalness of the synthetic speech, and listeners tended to prefer the voice created with the SCE inventory when the stimulus was an SCE passage. The procedures used in this project may be helpful for interventionists who wish to create synthetic voices with accents that are not commercially available.

Differences in Sibilant Perception between Gender Expansive and Cisgender Individuals.

Acoustic cues of voice gender influence not only how people perceive the speaker's gender (e.g., whether that person is a man, woman, or non-binary) but also how they perceive certain phonemes produced by that person. One such sociophonetic cue is the [s]/[ʃ] distinction in English; which phoneme is perceived depends on the perceived gender of the speaker. Recent research has shown that gender expansive people differ from cisgender people in their perception of voice gender and thus, this could be reflected in their categorization of sibilants. Despite this, there has been no research to date on how gender expansive people categorize sibilants. Furthermore, while voice gender expression is often discussed within a biological context (e.g., vocal folds), voice extends to those who use other communication methods. The current study fills this gap by explicitly recruiting people of all genders and asking them to perform a sibilant categorization task using synthetic voices. The results show that cisgender and gender expansive people perceive synthetic sibilants differently, especially from a "nonbinary" synthetic voice. These results have implications for developing more inclusive speech technology for gender expansive individuals, in particular for nonbinary people who use speech-generating devices.

Gender expansive listeners utilize a non-binary, multidimensional conception of gender to inform voice gender perception.

Few studies on voice perception have attempted to address the complexity of gender perception of ambiguous voices. The current study investigated how perception of gender varies with the complexity of the listener's own gender conception and identity. We explicitly recruited participants of all genders, including those who are gender expansive (i.e. transgender and/or non-binary), and directed them to rate ambiguous synthetic voices on three independent scales of masculine, feminine, and "other" (and to select one or multiple categorical labels for them). Gender expansive listeners were more likely to use the entire expanse of the rating scales and showed systematic categorization of gender-neutral voices as non-binary. We propose this is due to repeated use of reflective processes that challenge pre-existing gender categories and the incorporation of this decision-making process into their reflexive system. Because voice gender influences speech perception, the perceptual experience of gender expansive listeners may influence perceptual flexibility in speech.