Non-intrusive Quality Assessment of Synthesized Speech using Spectral Features and Support Vector Regression

Soni, Meet H.; Patil, Hemant A.

doi:10.21437/ssw.2016-21

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used non-intrusive speech quality assessment (NISQA) to predict the naturalness of the voices used in the experiment. NISQA is a model that can automatically evaluate super-wideband speech quality without the need for a clean reference signal [18]. The same model was used to predict the mean opinion score (MOS) in terms of the naturalness of the speech samples [19].…”

Section: Naturalnessmentioning

confidence: 99%

Influence of TTS Systems Performance on Reaction Times in People with Aphasia

et al. 2021

View full text Add to dashboard Cite

Text-to-speech (TTS) systems provide fundamental reading support for people with aphasia and reading difficulties. However, artificial voices are more difficult to process than natural voices. The current study is an extended analysis of the results of a clinical experiment investigating which, among three artificial voices and a digitised human voice, is more suitable for people with aphasia and reading impairments. Such results show that the voice synthesised with Ogmios TTS, a concatenative speech synthesis system, caused significantly slower reaction times than the other three voices used in the experiment. The present study explores whether and what voice quality metrics are linked to delayed reaction times. For this purpose, the voices were analysed using an automatic assessment of intelligibility, naturalness, and jitter and shimmer voice quality parameters. This analysis revealed that Ogmios TTS, in general, performed worse than the other voices in all parameters. These observations could explain the significantly delayed reaction times in people with aphasia and reading impairments when listening to Ogmios TTS and could open up consideration about which TTS to choose for compensative devices for these patients based on the voice analysis of these parameters.

show abstract

Section: Naturalnessmentioning

confidence: 99%

Influence of TTS Systems Performance on Reaction Times in People with Aphasia

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In [12] a double-ended speech naturalness model was presented that uses the English Blizzard Challenge data from 2008-2013 for training and evaluating with a per-system PCC of 0.84. In [13] a naturalness prediction model based on spectral features has been proposed that obtained PCCs between 0.69 and 0.89 on the Blizzard Challenge data from 2008-2010 and 2012. More recently, also, neural networks have been used to predict the naturalness of synthesized speech.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Assessment of Synthetic Speech Naturalness

Mittag

Möller

2020

Interspeech 2020

View full text Add to dashboard Cite

In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based on a CNN-LSTM network that previously showed to give good results for speech quality estimation. We trained and tested the model on 16 different datasets, such as from the Blizzard Challenge and the Voice Conversion Challenge. Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores. The proposed model is made publicly available and can, for example, be used to evaluate different TTS system configurations.

show abstract

“…Due to this limitation, there is an increasing focus on non-intrusive assessments. Any synthesized speech can be scored according to the predictions from machine learning models such as Support Vector Machines (Soni and Patil, 2016) and Neural…”

Section: Chapter I Introductionmentioning

confidence: 99%

Spectral and latent representation distortion for TTS evaluation

Kongthaworn

View full text Add to dashboard Cite

One of the main problems in the development of text-to-speech (TTS) systems is its reliance on subjective measures, typically the Mean Opinion Score (MOS). MOS requires a large number of people to reliably rate each utterance, making the development process slow and expensive. Recent research on speech quality assessment tends to focus on training models to estimate MOS, which requires a large number of training data, something that might not be available in low-resource languages. We propose an objective assessment metric based on the DTW distance using the spectrogram and the high-level features from an Automatic Speech Recognition (ASR) model to cover both acoustic and linguistic information. Experiments on Thai TTS and the Blizzard Challenge datasets show that our method outperformed other baselines in both utterance- and system-level by a large margin in terms of correlation coefficients. Our metric also outperformed the best baseline by 9.58% when used in head-to-head utterance-level comparisons. Ablation studies suggest that the middle layers of the ASR model are most suitable for TTS evaluation when used in conjunction with spectral features.

show abstract

Non-intrusive Quality Assessment of Synthesized Speech using Spectral Features and Support Vector Regression

Cited by 6 publications

References 11 publications

Influence of TTS Systems Performance on Reaction Times in People with Aphasia

Influence of TTS Systems Performance on Reaction Times in People with Aphasia

Deep Learning Based Assessment of Synthetic Speech Naturalness

Spectral and latent representation distortion for TTS evaluation

Contact Info

Product

Resources

About