Vocaine the vocoder and applications in speech synthesis

By Yannis Agiomyrgiannakis. 2015

76 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Generative Models, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Generative Models

In Signal Processing

Citations in the corpus

WaveNet: A Generative Model for Raw Audio (2016, methodology): “There have been a number of attempts to address these issues individually, such as developing high-quality vocoders (Kawahara et al., 1999; Agiomyrgiannakis, 2015; Morise et al., 2016), improving the accuracy of generative models (Zen et al., 2007; 2013; Fan et al., 2014; Uria et al., 2015), and…”
Tacotron: Towards End-to-End Speech Synthesis (2017, methodology): “For example, it is common for statistical parametric TTS to have a text frontend extracting various linguistic features, a duration model, an acoustic feature prediction model and a complex signal-processing-based vocoder (Zen et al., 2009; Agiomyrgiannakis, 2015).”
Deep Voice 3: 2000-Speaker Neural Text-to-Speech (2017, background): “It is also worth noting that there are numerous alternatives for high-quality hand-engineered vocoders in the literature, such as STRAIGHT (Kawahara et al., 1999), Vocaine (Agiomyrgiannakis, 2015), and WORLD (Morise et al., 2016).”
WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications (2016, methodology): “The use of a real-time synthe-sizer such as Vocaine [36] would be another way to improve WORLD.”
Fast, Compact, and High Quality LSTM-RNN Based Statistical Parametric Speech Synthesizers for Mobile Devices (2016, methodology): “05 kHz sampling, speech at 16 kHz sampling was synthesized at runtime using a resampling functionality in Vocaine [40].”
Probability density distillation with generative adversarial networks for high-quality parallel waveform generation (2019, background): “However, compared with traditional parametric vocoders [11–14], the WaveNet’s inference speed is inherently slow owing to its autoregressive model structure.”
Wasserstein GAN and Waveform Loss-Based Acoustic Model Training for Multi-Speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder (2018, methodology): “Finally, speech waveforms have been reconstructed using a deterministic vocoder based on the acoustic parameters [6] [7] [8].”
Postfilters to Modify the Modulation Spectrum for Statistical Parametric Speech Synthesis (2016, background): “There are three main reasons causing the quality degradation [11]: parameterization errors in the speech analysis/synthesis stage [27], [28], [29], inaccurate modeling in the training stage [18], [30], and over-smoothness of the generated speech parameters in the synthesis stage [25], [26].”
Voice Morphing that improves TTS quality using an optimal dynamic frequency warping-and-weighting transform (2016, methodology): “Following [2], the speech parameterization consists of 40-dimensional MCEP (including power), log f0 and a 7-dimensional band aperiodicity.”
Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning (2017, background): “There are also numerous alternatives for highquality hand-engineered vocoders in the literature, such as STRAIGHT (Kawahara et al., 1999), Vocaine (Agiomyrgiannakis, 2015), and WORLD (Morise et al., 2016).”
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (2019, methodology): “It turns out that the waveform generation methods based on the neural source-ﬁlter model, Vocaine, and Gri ﬃ n-Lim were not able to produce audio that shows more similarity to genuine speech under the current settings.”
An overview of voice conversion systems (2017, background): “Speech sigals can also be represented as a sum of non-stationary modulated inusoids; this has shown to significantly improve the synthesized peech quality in low-resource settings ( Agiomyrgiannakis, 2015 ).”
Improving FFTNet Vocoder with Noise Shaping and Subband Approaches (2018, methodology): “To improve the synthesized speech quality of conventional SPSS and VC over that offered by a simple mel-log spectrum approximation (MLSA) ﬁlter [3], several sophisticated corpus-independent vocoders have been developed [4–8].”
GlotNet—A Raw Waveform Model for the Glottal Excitation in Statistical Parametric Speech Synthesis (2019, background): “vanced aperiodicity models [10], [11], and direct modeling of”
Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model (2017, methodology): “For example, it is common for statistical parametric TTS to have a text frontend extracting various linguistic features, a duration model, an acoustic feature prediction model and a complex signal-processing-based vocoder (Zen et al., 2009; Agiomyrgiannakis, 2015).”