Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech

Merritt, Thomas; Latorre, Javier; King, Simon

doi:10.1109/icassp.2015.7178766

Cited by 17 publications

(27 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…a natural speech reference), significant improvements in subjective naturalness are obtained. However, none of the above techniques address what is perhaps the most fundamental problem of HMM-based speech synthesis: across-context averaging via decision tree clustering, which has been identified as a major contributing factor to reduced naturalness [8].…”

Section: A Related Workmentioning

confidence: 99%

Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

King

2016

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

We propose two novel techniquesstacking bottleneck features and minimum generation error training criterion -to improve the performance of deep neural network (DNN)based speech synthesis. The techniques address the related issues of frame-by-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNNbased synthesis frameworks. Stacking bottleneck features, which are an acoustically-informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation error training criterion minimises overall output trajectory error across an utterance, rather than minimising the error per frame independently, and thus takes into account the interaction between static and dynamic features. The two techniques can be easily combined to further improve performance. We present both objective and subjective results that demonstrate the effectiveness of the proposed techniques. The subjective results show that combining the two techniques leads to significantly more natural synthetic speech than from conventional DNN or long short-term memory (LSTM) recurrent neural network (RNN) systems.

show abstract

Section: A Related Workmentioning

confidence: 99%

Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

King

2016

IEEE/ACM Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In statistical parametric speech synthesis (SPSS), the vocoder has been identified a cause of "buzziness" and "phasiness" [1].…”

Section: Introductionmentioning

confidence: 99%

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

Espic

Botinhao²,

King

2017

Interspeech 2017

Self Cite

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

“…HMM 기반의 SPSS 방식에서 합성 음성의 품질을 저하시키는 원인 중의 하나는 문맥 요인을 포함시키는 음향 모델링의 구성 에 있다고 알려져 있다 (Ling et al, 2015;Zen et al, 2009 (Merritt et al, 2015;Yu et al, 2011). 그러므로 회귀 트리보다 성능이 우수한 모 델을 사용하는 방법을 모색할 필요성이 제기된다.…”

Section: 서론unclassified

Performance comparison of various deep neural network architectures using Merlin toolkit for a Korean TTS system*

Hong¹,

Kwon²

2019

Phonetics Speech Sci.

View full text Add to dashboard Cite

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

show abstract

Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech

Cited by 17 publications

References 19 publications

Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

Improving Trajectory Modelling for DNN-Based Speech Synthesis by Using Stacked Bottleneck Features and Minimum Generation Error Training

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

Performance comparison of various deep neural network architectures using Merlin toolkit for a Korean TTS system*

Contact Info

Product

Resources

About