A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis

Takaki, Shinji; Yamagishi, Junichi

doi:10.1109/icassp.2016.7472736

Cited by 33 publications

(19 citation statements)

References 21 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…modelling [5,6], duration modelling [7], feature extraction [8], and text analysis [9] having been investigated by various groups. It has been reported that DNN-based techniques have improved the quality of synthetic speech significantly; cf.…”

Section: Introductionmentioning

confidence: 99%

Adapting and controlling DNN-based speech synthesis using input codes

Luong

Takaki

Henter

et al. 2017

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Methods for adapting and controlling the characteristics of output speech are important topics in speech synthesis. In this work, we investigated the performance of DNN-based text-to-speech systems that in parallel to conventional text input also take speaker, gender, and age codes as inputs, in order to 1) perform multi-speaker synthesis, 2) perform speaker adaptation using small amounts of targetspeaker adaptation data, and 3) modify synthetic speech characteristics based on the input codes. Using a large-scale, studio-quality speech corpus with 135 speakers of both genders and ages between tens and eighties, we performed three experiments: 1) First, we used a subset of speakers to construct a DNN-based, multi-speaker acoustic model with speaker codes. 2) Next, we performed speaker adaptation by estimating code vectors for new speakers via backpropagation from a small amount of adaptation material. 3) Finally, we experimented with manually manipulating input code vectors to alter the gender and/or age characteristics of the synthesised speech. Experimental results show that high-performance multi-speaker models can be constructed using the proposed code vectors with a variety of encoding schemes, and that adaptation and manipulation can be performed effectively using the codes.

show abstract

Section: Introductionmentioning

confidence: 99%

Adapting and controlling DNN-based speech synthesis using input codes

Luong

Takaki

Henter

et al. 2017

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the adoption of non-parametric models has opened up possibilities for using higher-dimensional, correlated representations. In [12] a restricted Boltzmann machine (RBM) was used to model the spectral envelope distribution, and the reintroduction of neural networks [13] subsequently lead to work modelling higher dimensional representations [14,15] or modelling a conventional cepstral representation whilst optimising a cost function in the the waveform domain [16,17].…”

Section: Introductionmentioning

confidence: 99%

Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis

Espic

Botinhao²,

King

2017

Interspeech 2017

View full text Add to dashboard Cite

We propose a simple new representation for the FFT spectrum tailored to statistical parametric speech synthesis. It consists of four feature streams that describe magnitude, phase and fundamental frequency using real numbers. The proposed feature extraction method does not attempt to decompose the speech structure (e.g., into source+filter or harmonics+noise). By avoiding the simplifications inherent in decomposition, we can dramatically reduce the "phasiness" and "buzziness" typical of most vocoders. The method uses simple and computationally cheap operations and can operate at a lower frame rate than the 200 frames-per-second typical in many systems. It avoids heuristics and methods requiring approximate or iterative solutions, including phase unwrapping.Two DNN-based acoustic models were built -from male and female speech data -using the Merlin toolkit. Subjective comparisons were made with a state-of-the-art baseline, using the STRAIGHT vocoder. In all variants tested, and for both male and female voices, the proposed method substantially outperformed the baseline. We provide source code to enable our complete system to be replicated.

show abstract

“…Recently, various neural-networks-based models have been proposed to better map the textual features into acoustic ones [2,3]. There are also neural networks that directly model spectral features to avoid artifacts caused by vocoders [4,5].…”

Section: Introductionmentioning

confidence: 99%

An autoregressive recurrent mixture density network for parametric speech synthesis

Wang

Takaki

Yamagishi

2017

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Neural-network-based generative models, such as mixture density networks, are potential solutions for speech synthesis. In this paper we follow this path and propose a recurrent mixture density network that incorporates a trainable autoregressive model. An advantage of incorporating an autoregressive model is that the time dependency within acoustic feature trajectories can be modeled without using conventional dynamic features. More interestingly, experiments show that this autoregressive model learns to be a filter that emphasizes the high frequency components of the target acoustic feature trajectories in the training stage. In the synthesis stage, it boosts the low frequency components of the generated feature trajectories and hence increases their global variance. Experimental results show that the proposed model achieved higher likelihood on the training data and generated speech with better quality than other models when dynamic features were not utilized in any model.

show abstract

A deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes for statistical parametric speech synthesis

Cited by 33 publications

References 21 publications

Adapting and controlling DNN-based speech synthesis using input codes

Adapting and controlling DNN-based speech synthesis using input codes

Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis

An autoregressive recurrent mixture density network for parametric speech synthesis

Contact Info

Product

Resources

About