Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds

Kawahara, Hideki; Masuda-Katsuse, Ikuyo; Cheveigné, Alain de

doi:10.1016/s0167-6393(98)00085-5

Cited by 1,654 publications

(1,074 citation statements)

References 23 publications

Supporting

Mentioning

1,067

Contrasting

Unclassified

Order By: Relevance

“…The filter is often realised as minimum phase, derived by cepstral analysis of a smooth spectral envelope [2]. The source could be derived from the residual [3,4] or glottal signal [5], but is commonly just a pulse train / noise, alternating [6] or mixed [7].…”

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

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

show abstract

“…The 0th-through-59th mel-cepstral coefficients were used as the spectral parameter and F 0 and 5 band-aperiodicity [15], [16] were used as excitation parameters. The STRAIGHT analysis-synthesis system [17] was used for the parameter extraction and waveform synthesis. The 0th mel-cepstral coefficients of the input speech were directly used as those of the converted speech.…”

Section: Experimental Conditionsmentioning

confidence: 99%

Voice Conversion Using Input-to-Output Highway Networks

Saito

Takamichi

Saruwatari

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper proposes Deep Neural Network (DNN)-based Voice Conversion (VC) using input-to-output highway networks. VC is a speech synthesis technique that converts input features into output speech parameters, and DNN-based acoustic models for VC are used to estimate the output speech parameters from the input speech parameters. Given that the input and output are often in the same domain (e.g., cepstrum) in VC, this paper proposes a VC using highway networks connected from the input to output. The acoustic models predict the weighted spectral differentials between the input and output spectral parameters. The architecture not only alleviates over-smoothing effects that degrade speech quality, but also effectively represents the characteristics of spectral parameters. The experimental results demonstrate that the proposed architecture outperforms Feed-Forward neural networks in terms of the speech quality and speaker individuality of the converted speech. key words: statistical parametric speech synthesis, DNN-based voice conversion, highway networks, over-smoothing

show abstract

“…It is thus expected that all processors could be embedded into the electrolarynx and total latency will be decreased to the 50 msec caused by the real-time statistical F 0 prediction. ing the excitation signals based on the predicted F 0 values are artificially generated using the STRAIGHT [19] analysis/synthesis method.…”

Section: A Simulation Experimentsmentioning

confidence: 99%

“…As the source features, the spectral segment features were extracted from the mel-cepstra at the current ± 4 frames. On the other hand, F 0 values of normal speech were extracted with STRAIGHT F 0 analysis [19] and CF 0 patterns were generated as the target feature using a low-pass filter with 10 Hz cut-off frequency. Moreover, the target F 0 patterns were shifted so that their mean value was equal to 100 Hz to predict F 0 patterns suitable for the source male speaker.…”

Section: Experimental Conditionsmentioning

confidence: 99%

A Vibration Control Method of an Electrolarynx Based on Statistical <i>F</i><sub>0</sub> Pattern Prediction

Tanaka

Toda

Nakamura

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARY This paper presents a novel speaking aid system to help laryngectomees produce more naturally sounding electrolaryngeal (EL) speech. An electrolarynx is an external device to generate excitation signals, instead of vibration of the vocal folds. Although the conventional EL speech is quite intelligible, its naturalness suffers from the unnatural fundamental frequency (F 0 ) patterns of the mechanically generated excitation signals. To improve the naturalness of EL speech, we have proposed EL speech enhancement methods using statistical F 0 pattern prediction. In these methods, the original EL speech recorded by a microphone is presented from a loudspeaker after performing the speech enhancement. These methods are effective for some situation, such as telecommunication, but it is not suitable for face-to-face conversation because not only the enhanced EL speech but also the original EL speech is presented to listeners. In this paper, to develop an EL speech enhancement also effective for face-to-face conversation, we propose a method for directly controlling F 0 patterns of the excitation signals to be generated from the electrolarynx using the statistical F 0 prediction. To get an "actual feel" of the proposed system, we also implement a prototype system. By using the prototype system, we find latency issues caused by a real-time processing. To address these latency issues, we furthermore propose segmental continuous F 0 pattern modeling and forthcoming F 0 pattern modeling. With evaluations through simulation, we demonstrate that our proposed system is capable of effectively addressing the issues of latency and those of electrolarynx in term of the naturalness.

show abstract

Restructuring speech representations using a pitch-adaptive time–frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds

Cited by 1,654 publications

References 23 publications

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

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

Voice Conversion Using Input-to-Output Highway Networks

A Vibration Control Method of an Electrolarynx Based on Statistical <i>F</i><sub>0</sub> Pattern Prediction

Contact Info

Product

Resources

About