HMM-based Speech Synthesis System incorporated with Language Identification for Low-resourced Languages

Sefara, Tshephisho Joseph; Mokgonyane, Tumisho Billson; Manamela, Madimetja Jonas; Modipa, Thipe I.

doi:10.1109/icabcd.2019.8851055

Cited by 11 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many situations where the availability of such resources is not possible to achieve. For example, in building speech from historical recordings, children's speech and low resourced languages [13,14].…”

Section: Introductionmentioning

confidence: 99%

Measuring the Quality of Low-Resourced Statistical Parametric Speech Synthesis Trained with Noise-Degraded Data Supported by the University of Costa Rica

Coto-Jiménez¹

2022

CyS

View full text Add to dashboard Cite

After the successful implementation of speech synthesis in several languages, the study of robustness became an important topic so as to increase the possibility of building voices from non-standard sources, e.g. historical recordings, children's speech, and data freely available on the Internet. In this work, a measure of the influence of noise in the source speech of the statistical parametric speech synthesis system based on HMM is performed, for a case of a low-resourced database. For this purpose, three types of additive noise were considered at five signal-to-noise ratio levels to affect the source speech data. Using objective measures to assess the perceptual quality of the results and the propagation of the noise through all the processes of building speech synthesis, the results show a severe drop in the quality of artificial speech, even for the cases of lower levels of noise. Such degradation seems to be independent of the noise type, and is at lower proportion to the noise level. This results are of importance for any practical implementation of speech synthesis from degraded data in similar conditions, and shows that applying denoising processes became mandatory in order to keep the possibility of building intelligible voices.

show abstract

Section: Introductionmentioning

confidence: 99%

Measuring the Quality of Low-Resourced Statistical Parametric Speech Synthesis Trained with Noise-Degraded Data Supported by the University of Costa Rica

Coto-Jiménez¹

2022

CyS

View full text Add to dashboard Cite

show abstract

“…Speech naturalness can be described as how well the speech matches a listener's standards of rate, rhythm, intonation, and stress. Therefore, speech naturalness determines how natural the speech sounds to the listener and is compared to the speech they regularly hear in their immediate social environment [10]. Using a voice with a low level of naturalness, such as a robotic voice, does not match the human that it represents.…”

Section: Introductionmentioning

confidence: 99%

“…It appears listeners prefer a SGD to have a voice that is consistent with the characteristics of the person who is using it [2]. Pleasantness focuses on the pleasantness or agreeableness of the synthetic voice [10]. Although having a high quality and natural-sounding voice reduces listener fatigue and therefore contributes to positive attitudes towards the SGD by both the user and their conversational partners [9], it is also noteworthy to mention that listeners with greater exposure to synthesised speech, through practice effects, become better at analysing the acoustic-phonetic information in the signal, making better use of the acoustic cues in the synthesised speech, which results in increased intelligibility [11].…”

Section: Introductionmentioning

confidence: 99%

“…Thus, it is not improbable to consider that freely available software be used to assist individuals with CCN. However, these speech-synthesis systems are currently available for various major languages, such as English and other European languages, but are limited for South Africa's indigenous languages [10]. Accents also reflect the market size and English speech is therefore often US-accented [3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence

et al. 2022

View full text Add to dashboard Cite

(1) Background: Speech synthesis has customarily focused on adult speech, but with the rapid development of speech-synthesis technology, it is now possible to create child voices with a limited amount of child-speech data. This scoping review summarises the evidence base related to developing synthesised speech for children. (2) Method: The included studies were those that were (1) published between 2006 and 2021 and (2) included child participants or voices of children aged between 2–16 years old. (3) Results: 58 studies were identified. They were discussed based on the languages used, the speech-synthesis systems and/or methods used, the speech data used, the intelligibility of the speech and the ages of the voices. Based on the reviewed studies, relative to adult-speech synthesis, developing child-speech synthesis is notably more challenging. Child speech often presents with acoustic variability and articulatory errors. To account for this, researchers have most often attempted to adapt adult-speech models, using a variety of different adaptation techniques. (4) Conclusions: Adapting adult speech has proven successful in child-speech synthesis. It appears that the resulting quality can be improved by training a large amount of pre-selected speech data, aided by a neural-network classifier, to better match the children’s speech. We encourage future research surrounding individualised synthetic speech for children with CCN, with special attention to children who make use of low-resource languages.

show abstract

“…For under-resourced languages or the first development of artificial speech, HMM-based speech synthesis is a technique commonly applied in many cases [ 5 , 6 , 7 , 8 ]. Despite the advantages of this technique for speech synthesis, some shortcomings concerning naturalness and overall quality have been mentioned in the many implementations in languages around the world, often referred to as buzzy and muffled sound [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

Discriminative Multi-Stream Postfilters Based on Deep Learning for Enhancing Statistical Parametric Speech Synthesis

Coto-Jiménez

2021

Biomimetics

View full text Add to dashboard Cite

Statistical parametric speech synthesis based on Hidden Markov Models has been an important technique for the production of artificial voices, due to its ability to produce results with high intelligibility and sophisticated features such as voice conversion and accent modification with a small footprint, particularly for low-resource languages where deep learning-based techniques remain unexplored. Despite the progress, the quality of the results, mainly based on Hidden Markov Models (HMM) does not reach those of the predominant approaches, based on unit selection of speech segments of deep learning. One of the proposals to improve the quality of HMM-based speech has been incorporating postfiltering stages, which pretend to increase the quality while preserving the advantages of the process. In this paper, we present a new approach to postfiltering synthesized voices with the application of discriminative postfilters, with several long short-term memory (LSTM) deep neural networks. Our motivation stems from modeling specific mapping from synthesized to natural speech on those segments corresponding to voiced or unvoiced sounds, due to the different qualities of those sounds and how HMM-based voices can present distinct degradation on each one. The paper analyses the discriminative postfilters obtained using five voices, evaluated using three objective measures, Mel cepstral distance and subjective tests. The results indicate the advantages of the discriminative postilters in comparison with the HTS voice and the non-discriminative postfilters.

show abstract

HMM-based Speech Synthesis System incorporated with Language Identification for Low-resourced Languages

Cited by 11 publications

References 19 publications

Measuring the Quality of Low-Resourced Statistical Parametric Speech Synthesis Trained with Noise-Degraded Data Supported by the University of Costa Rica

Measuring the Quality of Low-Resourced Statistical Parametric Speech Synthesis Trained with Noise-Degraded Data Supported by the University of Costa Rica

A Situational Analysis of Current Speech-Synthesis Systems for Child Voices: A Scoping Review of Qualitative and Quantitative Evidence

Discriminative Multi-Stream Postfilters Based on Deep Learning for Enhancing Statistical Parametric Speech Synthesis

Contact Info

Product

Resources

About