Conventional and contemporary approaches used in text to speech synthesis: a review

Kaur, Navdeep; Singh, Parminder

doi:10.1007/s10462-022-10315-0

Cited by 28 publications

(12 citation statements)

References 135 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To create natural-sounding speech, various units are selected and concatenated according to the required text. There are two different approaches to concatenative speech synthesis: one uses Linear Predictive Coding (LPC) [4], and the other is based on Pitch-Synchronous Overlap and Add (PSOLA). The main drawbacks of these approaches are outlined in [5].…”

Section: Standard Speech Synthesis Systemmentioning

confidence: 99%

Current advances and algorithmic solutions in speech generation

Oralbekova,

Mamyrbayev,

Kassymova

et al. 2024

Vib. proced.

View full text Add to dashboard Cite

Currently, Text-to-Speech (TTS) technology, aimed at reproducing a natural human voice from text, is gaining increasing demand in natural language processing. Key criteria for evaluating the quality of synthesized sound include its clarity and naturalness, which largely depend on the accurate modeling of intonations using the acoustic model in the speech generation system. This paper presents fundamental methods such as concatenative and parametric speech synthesis, speech synthesis based on hidden Markov models, and deep learning approaches like end-to-end models for building the acoustic model. The article discusses metrics for evaluating the quality of synthesized voice. Brief overviews of modern text-to-speech architectures, such as WaveNet, Tacotron, and Deep Voice, applying deep learning and demonstrating quality ratings close to professionally recorded speech, are also provided.

show abstract

Section: Standard Speech Synthesis Systemmentioning

confidence: 99%

Current advances and algorithmic solutions in speech generation

Oralbekova,

Mamyrbayev,

Kassymova

et al. 2024

Vib. proced.

View full text Add to dashboard Cite

show abstract

“…For speech synthesis systems, it has been used for about two decades. A hidden Markov model is a collection of states connected by transitions with two sets of probabilities in each: a transition probability which provides the probability for taking this transition, and an output probability density function which defines the conditional probability of emitting each output symbol from a finite alphabet, given that the transition is taken [14] [15] [16].…”

Section: Development Of Electrical Synthesizersmentioning

confidence: 99%

A Review of Cross-Platform Document File Reader Using Speech Synthesis

Chukwudi,

Eze,

Chinyere

2023

International Journal of Artificial Intelligence

View full text Add to dashboard Cite

Document files are files used to store documents on storage devices primarily for computer use. Software is used to view these files, displaying their text content in a legible way. However, it is essential to have programs for transforming electronic files into versions usable by those who suffer from specific disabilities. This paper reviewed fifteen published articles in the field of document file reading. It was observed from the review that various attempts have been made by different researchers in order to develop a software cable for converting document files that consist of text to an audio format. Text may now be easily translated into natural-sounding voice across many platforms using different software. It was observed from the systematic review that the use of AI such as the GPT-3.5 and GPT-4 Turbo Large Language Model (LLM) technologies has the best performance because it does not end at producing a vocal sound that is similar to human own, but it also translates different languages. In conclusion, cross-platform document file reader (text-to-speech) synthesis has improved user experiences in a variety of applications such as language learning, audiobooks and virtual assistants.

show abstract

“…Speech synthesis has been extensively studied, particularly in the context of text-to-speech (TTS) systems (Ren et al, 2019 ; Kaur and Singh, 2022 ; Kumar et al, 2023 ). In the context of TTS technology, the traditional process involved three steps: (1) tokenizing the input text, (2) conducting rhyme analysis, and (3) searching and concatenating segmented speech units to convert the text into speech.…”

Section: Introductionmentioning

confidence: 99%

Attention-based speech feature transfer between speakers

Lee,

Cho,

Kwon

2024

Front. Artif. Intell.

View full text Add to dashboard Cite

In this study, we propose a simple yet effective method for incorporating the source speaker's characteristics in the target speaker's speech. This allows our model to generate the speech of the target speaker with the style of the source speaker. To achieve this, we focus on the attention model within the speech synthesis model, which learns various speaker features such as spectrogram, pitch, intensity, formant, pulse, and voice breaks. The model is trained separately using datasets specific to the source and target speakers. Subsequently, we replace the attention weights learned from the source speaker's dataset with the attention weights from the target speaker's model. Finally, by providing new input texts to the target model, we generate the speech of the target speaker with the styles of the source speaker. We validate the effectiveness of our model through similarity analysis utilizing five evaluation metrics and showcase real-world examples.

show abstract

Conventional and contemporary approaches used in text to speech synthesis: a review

Cited by 28 publications

References 135 publications

Current advances and algorithmic solutions in speech generation

Current advances and algorithmic solutions in speech generation

A Review of Cross-Platform Document File Reader Using Speech Synthesis

Attention-based speech feature transfer between speakers

Contact Info

Product

Resources

About