Speech synthesis

By M. Stella. 1986

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The HMM-based speech synthesis system (HTS) version 2.0 (2007, unknown): “The use of adaptive training enables us to estimate better canonical models for speaker adaptation and improves the performance of the average voice-based speech synthesis system [57].”
Synthesis of the Singing Voice by Performance Sampling and Spectral Models (2007, methodology): “The first digital physical model of the voice was based on simulating the vocal tract as a series of one-dimensional tubes [8], afterwards extended by means of digital waveguide synthesis [9] in the SPASM singing voice system [10].”
Statistical Parametric Speech Synthesis (2007, methodology): “Although this offers a ﬂ exible topology, it requires a search process for the state sequence at the synthesis stage (Eichner et al., 2001) because we need to determine a single-state sequence to generate speech parameters ef ﬁ ciently using the speech parameter generation algorithm (the Case 1…”
Singing synthesis as a new musical instrument (2012, methodology): “Singing synthesis dates back to a research by Kelly et al. [1] in 1962.”