Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates features (e.g., mel-spectrogram) given a music score. Previous models adopt simple loss L1 L2) or generative adversarial network (GAN) reconstruct features, while they suffer from over-smoothing unstable training issues respectively, hinder naturalness o...

OBJECTIVES Relative fundamental frequency (RFF) has shown promise as an acoustic measure of voice, but the subjective and time-consuming nature of its manual estimation has made clinical translation infeasible. Here, a faster, more objective algorithm for RFF estimation is evaluated in a large and diverse sample of individuals with and without voice disorders. METHODS Acoustic recordings were...

Studies of brain-damaged subjects indicate that recognizing a familiar voice and discriminating among unfamiliar voices may be selectively impaired, and thus that the two are separate functions. Familiar voice recognition was impaired in cases of damage to the right (but not the left) hemisphere, while impaired unfamiliar voice discrimination was observed in cases with damage to either hemisphere.

Voice over Internet Protocol is a technology of transmitting voice on the Internet. Human voice is digitized, encoded, and transmitted on the Internet in the form of voice packets. These packets are received at the other end, decoded and converted back to analog signal. Loss and delay of voice packets result in the degradation of voice quality, since voice is a real-time application. Consecutiv...

in their valuable discussion of whistleblowing in healthcare organisations, mannion and davies highlight the importance of organisational culture in influencing whether people raise concerns, and whether these concerns are listened to and acted upon. the role of leadership in shaping organisational culture is well-established1 and in this commentary, we will examine the influence of leaders in ...