Instantaneous pitch estimation algorithm based on multirate sampling

Azarov, Elias; Vashkevich, Maxim; Petrovsky, Alexander

doi:10.1109/icassp.2016.7472623

Cited by 14 publications

(14 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For F0 mapping from the neutral to the target emotion, the parameters were tuned in the manner described herein. For F0 feature extraction, 25-ms analysis frames with 5-ms frame shift were employed using a robust algorithm for pitch tracking [78], with frequencies varying from 50 to 500 Hz. For wavelet decomposition and ANN mapping, the F0 contour must be continuous.…”

Section: Experimental Set-upmentioning

confidence: 99%

Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network

et al. 2020

View full text Add to dashboard Cite

We propose a hybrid network-based learning framework for speaker-adaptive vocal emotion conversion, tested on three different datasets (languages), namely, EmoDB (German), IITKGP (Telugu), and SAVEE (English). The optimized learning model introduced is unique because of its ability to synthesize emotional speech with an acceptable perceptive quality while preserving speaker characteristics. The multilingual model is extremely beneficial in scenarios wherein emotional training data from a specific target speaker are sparsely available. The proposed model uses speaker-normalized mel-generalized cepstral coefficients for spectral training with data adaptation using the seed data from the target speaker. The fundamental frequency (F0) is transformed using a wavelet synchrosqueezed transform prior to mapping to obtain a sharpened time-frequency representation. Moreover, a feedforward artificial neural network, together with particle swarm optimization, was used for F0 training. Additionally, static-intensity modification was also performed for each test utterance. Using the framework, we were able to capture the spectral and pitch contour variabilities of emotional expression better than with other state-of-the-art methods used in this study. Considering the overall performance scores across datasets, an average melcepstral distortion (MCD) of 4.98 and root mean square error (RMSE-F0) of 10.67 were obtained in objective evaluations, and an average comparative mean opinion score (CMOS) of 3.57 and speaker similarity score of 3.70 were obtained for the proposed framework. Particularly, the best MCD of 4.09 (EmoDB-happiness) and RMSE-F0 of 9.00 (EmoDB-anger) were obtained, along with the maximum CMOS of 3.7 and speaker similarity of 4.6, thereby highlighting the effectiveness of the hybrid network model.

show abstract

Section: Experimental Set-upmentioning

confidence: 99%

Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The improved RAPT named as IRAPT (Instantaneous RAPT) has been proposed that introduces instantaneous harmonics [ 10]. In [10], F o estimation is realized by using instantaneous frequency instead of NCCF (Normalized Cross Correlation Function) and input speech is time-warped by the estimated F o and F o is re-estimated by using the time-warped speech. Instantaneous harmonic in IRAPT method is calculated from speech, however the complex residual estimated by the TV-CAR analysis can be applied.…”

Section: Introductionmentioning

confidence: 99%

On a robust F<inf>0</inf> estimation of speech based on IRAPT using robust TV-CAR analysis

Hotta

Funaki

2014

Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific

View full text Add to dashboard Cite

Fundamental frequency (Fa) estimation is important in speech processing such as speech coding, synthesis, recognition and so on. A present Fa estimation method performs well under clean condition, however the performance deteriorates significantly in noisy environment. As a result, robust Fa estimation against additive noise is demanded. We have previously proposed Fa estimation methods based on Time-Varying Complex AR (TV-CAR) analysis whose criterion is the weighted correlation of the complex residual obtained by the TV-CAR analysis, sum of the harmonics for the complex residual spectrum, or so on. On the other hand, E.Azarov et at. have proposed an improved method of RAPT (Robust Algorithm for Pitch Tracking) using an instantaneous harmonics that is called IRAPT (Instantaneous RAPT). The IRAPT can perform better estimation than RAPT. Since IRAPT uses band-limited analytic signal to obtain harmonic frequencies, the complex residual signal obtained by the TV-CAR analysis can also be applied to the IRAPT. In this paper, novel Fa estimation method using the instantaneous frequency based on the robust ELS (Extended Least Square) TV-CAR residual is proposed and evaluated.

show abstract

“…Other implementations addressing the problem of pitch detection with low time lag can be found, e.g., in the field of audio to MIDI conversion [13], where F 0 is estimated from a given set of partials for musical instruments based on a probabilistic model or in an instantaneous implementation of the RAPT framework [14] which has a higher inherent time lag compared with typical lags of the AAC or our used reference algorithms. A different approach is parametric pitch estimation routines (e.g., [15]) which assume a predetermined model for the estimation of the signal under investigation.…”

Section: Reference Algorithmsmentioning

confidence: 99%

Fast fundamental frequency determination via adaptive autocorrelation

Staudacher

Steixner

Griessner

et al. 2016

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

We present an algorithm for the estimation of fundamental frequencies in voiced audio signals. The method is based on an autocorrelation of a signal with a segment of the same signal. During operation, frequency estimates are calculated and the segment is updated whenever a period of the signal is detected. The fast estimation of fundamental frequencies with low error rate and simple implementation is interesting for real-time speech signal processing.

show abstract

Instantaneous pitch estimation algorithm based on multirate sampling

Cited by 14 publications

References 12 publications

Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network

Emotional Voice Conversion Using a Hybrid Framework With Speaker-Adaptive DNN and Particle-Swarm-Optimized Neural Network

On a robust F<inf>0</inf> estimation of speech based on IRAPT using robust TV-CAR analysis

Fast fundamental frequency determination via adaptive autocorrelation

Contact Info

Product

Resources

About