GlotNet—A Raw Waveform Model for the Glottal Excitation in Statistical Parametric Speech Synthesis

Juvela, Lauri; Bollepalli, Bajibabu; Tsiaras, Vassilis; Alku, Paavo

doi:10.1109/taslp.2019.2906484

Cited by 43 publications

(33 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, similar studies reporting variations in the WaveNet performance (depending on speaker and acoustic features) are found in the literature: MOS scores around 3.5 have been reported when using mel-filterbank [36] or melcepstrum [7] acoustic features. Meanwhile, our version of WaveNet has previously achieved MOS scores above 4 using glottal vocoder acoustic features [17]. The performance of a parallel waveform generator is likely to increase with the use of a separate pitch predictor model [15].…”

Section: Discussionmentioning

confidence: 99%

“…However, the intended use of phase recovery in Tacotron-based synthesis is generally not high-quality synthesis, but rather a development tool to quickly check whether the generated acoustic features are meaningful. For a reference autoregressive WaveNet vocoder, we trained a speaker dependent model conditioned on mel-spectrograms, following the "Wave-30" configuration from [17]. The system uses a dilation cycle of 10 (e.g., 1, 2, ..., 512) repeated three times, 64 residual channels, and 256 post-net channels.…”

Section: Reference Methodsmentioning

confidence: 99%

“…However, this approach requires explicit voicing and pitch inputs, and is sensitive to the alignment between generated and target signals when STFT phase loss is used. Meanwhile, the source-filter model has also been used with linear predictive (LP) filters to build neural models for the glottal excitation [16,17] or the LP residual signal [18,19]. The use of LP inverse filtering can be seen analogous to the the flow-based approaches, as they apply an invertible transform whose residual is more Gaussian and is thus easier to model [17].…”

Section: Introductionmentioning

confidence: 99%

“…Meanwhile, the source-filter model has also been used with linear predictive (LP) filters to build neural models for the glottal excitation [16,17] or the LP residual signal [18,19]. The use of LP inverse filtering can be seen analogous to the the flow-based approaches, as they apply an invertible transform whose residual is more Gaussian and is thus easier to model [17]. However, these LP-based models still use sequential inference (similar to WaveNet or WaveRNN) and the inherent speed limitations remain in place.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-Spectrogram

Juvela¹,

Bollepalli²,

Yamagishi

et al. 2019

Interspeech 2019

Self Cite

View full text Add to dashboard Cite

Recent advances in neural network -based text-to-speech have reached human level naturalness in synthetic speech. The present sequence-to-sequence models can directly map text to mel-spectrogram acoustic features, which are convenient for modeling, but present additional challenges for vocoding (i.e., waveform generation from the acoustic features). Highquality synthesis can be achieved with neural vocoders, such as WaveNet, but such autoregressive models suffer from slow sequential inference. Meanwhile, their existing parallel inference counterparts are difficult to train and require increasingly large model sizes. In this paper, we propose an alternative training strategy for a parallel neural vocoder utilizing generative adversarial networks, and integrate a linear predictive synthesis filter into the model. Results show that the proposed model achieves significant improvement in inference speed, while outperforming a WaveNet in copy-synthesis quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Reference Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-Spectrogram

Juvela¹,

Bollepalli²,

Yamagishi

et al. 2019

Interspeech 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…There have been several attempt to incorporate the LP filter into autoregressive neural vocoding systems. For instance, GlotNet and ExcitNet used the WaveNet structure to generate the glottal exci-tation [9,10]. In case of the LPCNet, it employed the lightweight WaveRNN model for fast generation of the excitation.…”

Section: Relationship To Prior Workmentioning

confidence: 99%

Improving LPCNET-Based Text-to-Speech with Linear Prediction-Structured Mixture Density Network

Hwang

Song

Yamamoto

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we propose an improved LPCNet vocoder using a linear prediction (LP)-structured mixture density network (MDN). The recently proposed LPCNet vocoder has successfully achieved high-quality and lightweight speech synthesis systems by combining a vocal tract LP filter with a WaveRNN-based vocal source (i.e., excitation) generator. However, the quality of synthesized speech is often unstable because the vocal source component is insufficiently represented by the µ-law quantization method, and the model is trained without considering the entire speech production mechanism. To address this problem, we first introduce LP-MDN, which enables the autoregressive neural vocoder to structurally represent the interactions between the vocal tract and vocal source components. Then, we propose to incorporate the LP-MDN to the LPCNet vocoder by replacing the conventional discretized output with continuous density distribution. The experimental results verify that the proposed system provides high quality synthetic speech by achieving a mean opinion score of 4.41 within a text-to-speech framework.

show abstract

APNet2: High-Quality and High-Efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra

Du,

Lu,

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

GlotNet—A Raw Waveform Model for the Glottal Excitation in Statistical Parametric Speech Synthesis

Cited by 43 publications

References 35 publications

GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-Spectrogram

GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-Spectrogram

Improving LPCNET-Based Text-to-Speech with Linear Prediction-Structured Mixture Density Network

APNet2: High-Quality and High-Efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra

Contact Info

Product

Resources

About