Quality Assessment of HMM-Based Speech Synthesis Using Acoustical Vowel Analysis

Coto-Jiménez, Marvin; Goddard-Close, John; Licona, Fabiola Martínez

doi:10.1007/978-3-319-11581-8_46

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our first results with statistical parametric speech synthesis using HTS to produce voices in Mexican Spanish would have shown the advantages of using this technique, and have been documented in [22][23][24]. Those results were reported without any deep learning algorithms involved, and showed the improvement opportunities in que quality of the voices.…”

Section: Results Achievedmentioning

confidence: 53%

Speech Synthesis Based on Hidden Markov Models and Deep Learning

Coto-Jiménez¹,

Goddard-Close²

2016

RCS

Self Cite

View full text Add to dashboard Cite

Speech synthesis based on Hidden Markov Models (HMM) and other statistical parametric techniques have been a hot topic for some time. Using this techniques, speech synthesizers are able to produce intelligible and flexible voices. Despite progress, the quality of the voices produced using statistical parametric synthesis has not yet reached the level of the current predominant unit-selection approaches, that select and concatenate recordings of real speech. Researchers now strive to create models that more accurately mimic human voices. In this paper, we present our proposal to incorporate recent deep learning algorithms, specially the use of Long Short-term Memory (LSTM) to improve the quality of HMM-based speech synthesis. Thus far, the results indicate that HMM-voices can be improved using this approach in its spectral characteristics, but additional research should be conducted to improve other parameters of the voice signal, such as energy and fundamental frequency, to obtain more natural sounding voices.

show abstract

Section: Results Achievedmentioning

confidence: 53%

Speech Synthesis Based on Hidden Markov Models and Deep Learning

Coto-Jiménez¹,

Goddard-Close²

2016

RCS

Self Cite

View full text Add to dashboard Cite

show abstract

Region Normalized Capsule Network Based Generative Adversarial Network for Non-parallel Voice Conversion

Akhter,

Banerjee,

Dhar

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Análisis acústico de vocales de niños costarricenses

Coto-Jiménez

Rodríguez

2020

RFL

View full text Add to dashboard Cite

En este artículo se presenta un análisis acústico de vocales pronunciadas por niños costarricenses con edades entre los 6 y los 12 años. Estos análisis tienen como objetivo lograr una mejor comprensión de las características del habla producidas por este grupo en particular y, de esta manera, brindar información importante para la mejora de los reconocedores automáticos del habla y la identificación del hablante. Para este propósito, se construyó una base de datos con palabras aisladas que contemplan los fonemas, de acuerdo con varias etapas del desarrollo del lenguaje. Adicionalmente, se desarrolló una estrategia para la interacción con los niños. Los resultados confirman y complementan los resultados reportados en la literatura, pues muestran que existe una mayor variabilidad en parámetros como los formantes, la duración y el tono de las vocales emitidas por los niños, en comparación con los adultos. Los resultados permiten caracterizar cuantitativamente estos sonidos del habla, y establecer futuras investigaciones en áreas como el reconocimiento de habla y su dependencia del género y la edad dentro de esta comunidad.

show abstract

Quality Assessment of HMM-Based Speech Synthesis Using Acoustical Vowel Analysis

Cited by 3 publications

References 13 publications

Speech Synthesis Based on Hidden Markov Models and Deep Learning

Speech Synthesis Based on Hidden Markov Models and Deep Learning

Region Normalized Capsule Network Based Generative Adversarial Network for Non-parallel Voice Conversion

Análisis acústico de vocales de niños costarricenses

Contact Info

Product

Resources

About