An introduction to text-to-speech synthesis

By Thierry Dutoit. 1997

How researchers see this paper

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

Citations in the corpus

Sample Efficient Adaptive Text-to-Speech (2018, neutral): “TTS techniques require hours of high-quality recordings, collected in controlled environments, for each new voice style.”
Introduction to Digital Speech Processing (2007, methodology): “Various smoothing methods based on the concepts of time domain harmonic scaling (TDHS) [76] and pitch synchronous overlap add (PSOLA) [20, 31, 82] have been proposed and optimized for such smoothing/modification at the boundaries between adjacent diphone units.”
Fftnet: A Real-Time Speaker-Dependent Neural Vocoder (2018, background): “The approach has many applications, including the classical text-to-speech (TTS) problem [2].”
Multi-Lingual Multi-Speaker Text-to-Speech Synthesis for Voice Cloning with Online Speaker Enrollment (2020, background): “In traditional text-to-speech (TTS) synthesis methods [1], many system components such as the grapheme-to-phoneme model, phoneme duration model, segmentation model, fundamental frequency estimation model and synthesis model are trained separately, and they require expert domain knowledge to produce ”
Cross-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning without Using Parallel Corpus for Unseen Speakers (2019, background): “In traditional text-to-speech (TTS) synthesis methods [1], many system components such as the grapheme-to-phoneme model, phoneme duration model, segmentation model, fundamental frequency estimation model and synthesis model are trained separately, and they require expert domain knowledge to produce ”
The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching (2003, methodology): “The architecture of the MARY TtS system is similar to a typical TtS architecture as described by Dutoit [6].”
Aibo''s first words. the social learning of language and meaning. Evolution of Communication (2002, methodology): “The speech synthesis system is a state of the art text-to-speech synthesiser, similar to the one described in [Dutoit, 1997].”
Virtual Phone Discovery for Speech Synthesis Without Text (2019, background): “Building Text-to-speech (TTS) synthesis system generally requires speech, text and/or linguistic information [13].”
Speaker Conditional WaveRNN: Towards Universal Neural Vocoder for Unseen Speaker and Recording Conditions (2020, unknown): “Speech synthesis has received attention in the research community as voice interaction systems have been implemented in various applications, such as personalized Text-to-Speech (TTS) systems, voice conversion, dialogue systems and navigations [1, 2, 3, 4].”
Automatic Analysis of Prosody for Multi‐lingual Speech Corpora (2002, methodology): “experiments, however, (Di Cristo & Hirst 1997, Malfrère & Dutoit 1997) have shown that a fairly accurate alignment of phonemic labels can be obtained without prior training by using a diphone synthesis system such as Mbrola (Dutoit 1997).”
Text-to-Speech Synthesis (2009, background): “Dutoit [148] stands out as being one of the few books t tackle the signal processing issue from a TTS only perspective, describing all the algorithms m entioned here in considerable detail.”