Non-Autoregressive vs Autoregressive Neural Networks for System Identification

Weber, Daniel; Gühmann, Clemens

doi:10.1016/j.ifacol.2021.11.252

“…Most state-of-the-art speech synthesis models use an autoregressive-based decoder, where the prediction is sequential. The autoregressive models require significantly more inference time than the non-autoregressive models, which are at least as accurate as the autoregressive models [28]. The accuracy of speech synthesis models can be improved by incorporating the knowledge of human speech production mechanism.…”

Section: F 0 Estimatormentioning

confidence: 99%

Prosody-TTS: An end-to-end speech synthesis system with prosody control

Pamisetty¹,

Murty²

2021

Preprint

0

View full text Add to dashboard Cite

End-to-end text-to-speech synthesis systems achieved immense success in recent times, with improved naturalness and intelligibility. However, the end-toend models, which primarily depend on the attention-based alignment, do not offer an explicit provision to modify/incorporate the desired prosody while synthesizing the signal. Moreover, the state-of-the-art end-to-end systems use autoregressive models for synthesis, making the prediction sequential. Hence, the inference time and the computational complexity are quite high. This paper proposes Prosody-TTS, an end-to-end speech synthesis model that combines the advantages of statistical parametric models and end-to-end neural network models. It also has a provision to modify or incorporate the desired prosody by controlling the fundamental frequency (f 0 ) and the phone duration. Generating speech samples with appropriate prosody and rhythm helps in improving the naturalness of the synthesized speech. We explicitly model the duration of the phoneme and the f 0 to have control over them during the synthesis. The model is trained in an end-toend fashion to directly generate the speech waveform from the input text, which in turn depends on the auxiliary subtasks of predicting the phoneme duration, f 0 , and mel spectrogram. Experiments on the Telugu language data of the IndicTTS database show that the proposed Prosody-TTS model achieves state-of-the-art performance with a mean opinion score of 4.08, with a very low inference time.

show abstract

“…However, researchers tend to adopt non-autoregressive models for tackling time series analysis more and more. Weber et al[69]…”

mentioning

confidence: 99%

Multivariate Time Series Imputation: A Survey on available Methods with a Focus on hybrid GANs

Richter¹,

Ijaradar²,

Wetzker³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

<p>Multivariate time series (MTS) are captured in a great variety of real-world applications. However, analysing and modelling the data for classification and forecasting purposes can become very challenging if values are missing in the data set. The need for imputation methods, to fill the gaps in MTS, is well known. Thus, a great variaty of algorithms for solving this task has been proposed in the literature. However, research community is constantly working on the development of advanced algorithms, that fulfill the special requirements of multidimensional temporal data, since most of the existing imputation methods treat MTS as ordinary structured data and fail to model the temporal relationships within and between sequences of observations. The main emphasis of MTS imputation research is currently put on deep learning (DL) models, especially models making use of generative adversarial networks (GANs). In our survey, we present a general categorization of imputation algorithms and introduce groups of hybrid GAN-models used for the MTS imputation task, which we investigate and discuss in detail. A quantitative comparison of the hybrid GANs’ performance regarding MTS imputation is presented based on our findings in the literature. </p>

show abstract

“…However, researchers tend to adopt non-autoregressive models for tackling time series analysis more and more. Weber et al[69]…”

mentioning

confidence: 99%

Multivariate Time Series Imputation: A Survey on available Methods with a Focus on hybrid GANs

Richter¹,

Ijaradar²,

Wetzker³

et al. 2022

Preprint

0

View full text Add to dashboard Cite

<p>Multivariate time series (MTS) are captured in a great variety of real-world applications. However, analysing and modelling the data for classification and forecasting purposes can become very challenging if values are missing in the data set. The need for imputation methods, to fill the gaps in MTS, is well known. Thus, a great variaty of algorithms for solving this task has been proposed in the literature. However, research community is constantly working on the development of advanced algorithms, that fulfill the special requirements of multidimensional temporal data, since most of the existing imputation methods treat MTS as ordinary structured data and fail to model the temporal relationships within and between sequences of observations. The main emphasis of MTS imputation research is currently put on deep learning (DL) models, especially models making use of generative adversarial networks (GANs). In our survey, we present a general categorization of imputation algorithms and introduce groups of hybrid GAN-models used for the MTS imputation task, which we investigate and discuss in detail. A quantitative comparison of the hybrid GANs’ performance regarding MTS imputation is presented based on our findings in the literature. </p>

show abstract

Non-Autoregressive vs Autoregressive Neural Networks for System Identification

Cited by 7 publications

References 22 publications

Prosody-TTS: An end-to-end speech synthesis system with prosody control

Prosody-TTS: An end-to-end speech synthesis system with prosody control

Multivariate Time Series Imputation: A Survey on available Methods with a Focus on hybrid GANs

Multivariate Time Series Imputation: A Survey on available Methods with a Focus on hybrid GANs

Contact Info

Product

Resources

About