Multi-stage children story speech synthesis for Hindi
DM Harikrishna, G Reddy… - 2015 Eighth International …, 2015 - ieeexplore.ieee.org
In this paper, we propose a multi-stage children story speech synthesis system for Hindi
language. The proposed system performs the following tasks:(i) classification of stories into …
language. The proposed system performs the following tasks:(i) classification of stories into …
[PDF][PDF] Overview of NITECH HMM-based text-to-speech system for Blizzard Challenge 2014
K Sawada, S Takaki, K Hashimoto, K Oura… - Blizzard Challenge …, 2014 - festvox.org
This paper describes a hidden Markov model based text-tospeech (TTS) system developed
at the Nagoya Institute of Technology (NITECH) for Blizzard Challenge 2014. The tasks of …
at the Nagoya Institute of Technology (NITECH) for Blizzard Challenge 2014. The tasks of …
The IRISA text-to-speech system for the Blizzard challenge 2017
This paper describes the implementation of the IRISA unit selection-based TTS system for
our participation to the Blizzard Challenge 2017. We describe the process followed to build …
our participation to the Blizzard Challenge 2017. We describe the process followed to build …
Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language
Phonetic segmentation plays a key role in developing various speech applications. In this
work, we propose to use various features for automatic phonetic segmentation task for …
work, we propose to use various features for automatic phonetic segmentation task for …
Exploring Solutions for Text-to-Speech Synthesis of Low-Resource Languages
AR Gladston, KV Pradeep - 2023 4th International Conference …, 2023 - ieeexplore.ieee.org
A text-to-speech synthesis system is expected to convert any given text to highly intelligible
and natural speech that sounds as human-like as possible. It finds its place in a variety of …
and natural speech that sounds as human-like as possible. It finds its place in a variety of …
Analysis of natural and synthetic speech using Fujisaki model
Text-to-speech (TTS) synthesis systems are being advanced to achieve naturalness and
intelligibility in synthetic speech. Unit selection-based synthesis (USS) and Hidden Markov …
intelligibility in synthetic speech. Unit selection-based synthesis (USS) and Hidden Markov …
[PDF][PDF] Segmental evaluation of Text-to-Speech Synthesizers
A Pandey - 2024 - tara.tcd.ie
Advancements in speech synthesis technology have mandated the need for reliable
methods for its evaluation. Present day evaluation, dominated by subjective listening tests …
methods for its evaluation. Present day evaluation, dominated by subjective listening tests …
[PDF][PDF] Exploring text to speech synthesis in non-standard languages
The development of Text to Speech synthesis systems as part of the Human Language
Technology is a dominating research field in the present age. Languages are the backbone …
Technology is a dominating research field in the present age. Languages are the backbone …
Analysis of Prosodic features for the degree of emotions of an Assamese Emotional Speech
S Bharadwaj, PB Acharjee - 2020 4th International Conference …, 2020 - ieeexplore.ieee.org
This research work has attempted to study the speech prosody for designing a speech
synthesizer. Speech prosody carries all relevant information about the utterances. Here, it …
synthesizer. Speech prosody carries all relevant information about the utterances. Here, it …
TTS evaluation: Double-ended objective quality measures
S Rao, C Mahima, S Vishnu, S Adithya… - 2015 IEEE …, 2015 - ieeexplore.ieee.org
We address the problem of TTS speech quality evaluation and propose a double-ended
objective measure in the form of average spectral distortion between time-aligned reference …
objective measure in the form of average spectral distortion between time-aligned reference …