Pitch Synchronization Research Articles

Spoofing Speech Detection Using Modified Relative Phase Information

The detection of human and spoofing (synthetic or converted) speech has started to receive an increasing amount of attention. In this paper, modified relative phase (MRP) information extracted from a Fourier spectrum is proposed for spoofing speech detection. Because original phase information is almost entirely lost in spoofing speech using current synthesis or conversion techniques, some phase information extraction methods, such as the modified group delay feature and cosine phase feature, have been shown to be effective for detecting human speech and spoofing speech. However, existing phase information-based features cannot obtain very high spoofing speech detection performance because they cannot extract precise phase information from speech. Relative phase (RP) information, which extracts phase information precisely, has been shown to be effective for speaker recognition. In this paper, RP information is applied to spoofing speech detection, and it is expected to achieve better spoofing detection performance. Furthermore, two modified processing techniques of the original RP, that is, pseudo pitch synchronization and linear discriminant analysis based full-band RP extraction, are proposed in this paper. In this study, MRP information is also combined with the Mel-frequency cepstral coefficient (MFCC) and modified group delay. The proposed method was evaluated using the ASVspoof 2015: Automatic Speaker Verification Spoofing and Countermeasures Challenge dataset. The results show that the proposed MRP information significantly outperforms the MFCC, modified group delay, and other phase information based features. For the development dataset, the equal error rate (EER) was reduced from 1.883% of the MFCC, 0.567% of the modified group delay to 0.013% of the MRP. By combining the RP with the MFCC and modified group delay, the EER was reduced to 0.003%. For the evaluation dataset, the MRP obtained much better performance than the magnitude-based feature and other phase-based features, except for S10 spoofing speech.

Voice source characterization using pitch synchronous discrete cosine transform for speaker identification.

A characterization of the voice source (VS) signal by the pitch synchronous (PS) discrete cosine transform (DCT) is proposed. With the integrated linear prediction residual (ILPR) as the VS estimate, the PS DCT of the ILPR is evaluated as a feature vector for speaker identification (SID). On TIMIT and YOHO databases, using a Gaussian mixture model (GMM)-based classifier, it performs on par with existing VS-based features. On the NIST 2003 database, fusion with a GMM-based classifier using MFCC features improves the identification accuracy by 12% in absolute terms, proving that the proposed characterization has good promise as a feature for SID studies.

Single channel speech dereverberation based on modified cepstral co-efficients

Linear prediction is the widely used method for obtaining all-pole speech representations. But in many cases spectral zeroes also plays a vital role in speech enhancement. So there is need of designing general modelling method for this purpose. Besides this, the requirement of pitch synchronization made the flexibility of existing algorithms limited. This paper exploits a novel approach on pole-zero analysis called cepstrum analysis, which can avoid synchronization problems. Dereverberation is performed based on cepstral separation on non-minimum phase signals. The technique works by flattening the magnitude of non-minimum phase signals prior to phase distortion. The proposed method is superior to standard linear prediction techniques as it overcomes the computational errors inflicted due to long time responses of all-pole inverse filters. The algorithm explores speech dereverberation techniques, whose principle is recovery of envelope variations of original speech (Langhans and Strube, Speech enhancement by nonlinear multiband envelope filtering, 1982; Hirsch, Automatic speech recognition in rooms, 1988). Results of the preliminary evaluation on reverberant speech using signal to reverberation ratio are analysed and discussed.

Application of pitch synchronization dynamic frame-length features in English lexical stress detection

Lexical stress is an important prosodic feature,especially for stress-timed language such as English.To overcome the defects of fixed frame-length features,pitch synchronization feature analysis method was proposed while Pitch Synchronization Energy(PSE) and Pitch Synchronization Peak(PSP) features were defined and extracted.Their contributions,along with traditional features and their combinations,to English lexical stress detection were evaluated with ISLE database.Experimental results show that the combination of new feature and traditional features demonstrates a 6.65% error rate reduction compared with using traditional ones.

A Pitch-Synchronous Extension of Fractal Additive Synthesis via Time-Varying Cosine Modulated Filter Banks

Fractal additive synthesis (FAS) is a method for the synthesis-by-analysis of voiced-sounds. FAS is based on a harmonic version of the wavelet transform (WT), and it allows to define two different parametric models for the deterministic and the stochastic components of sounds, respectively. In this letter, we introduce a pitch-synchronous (PS) extension of FAS. By adapting an already existing method for the design of time-varying cosine modulated filter banks (TV-CMFB), we are now able to deal with a much wider class of voiced-sounds, i.e., any voiced-sound showing a variable pitch as in the case, for example, of glissando or vibrato effects.

Innovative wavelet based speech model using optimal mother wavelet generated from pitch synchronous LPC trajectory

The paper proposes an innovative technique for generation of optimal mother wavelet using LPC trajectory with special reference to speech recognition. A new wavelet based model is proposed for speech signal processing. Lower order linear predictor coefficients (LPC) are related to the vocal tract area near lip that is the articulating organ. The trajectory of second LPC is proposed for the generation of mother wavelet for speech recognition. The observation interval is selected as the pitch period that represents one complete cycle of speech waveform. LPC of order 10 are evaluated for each pitch synchronous (PS) segment. An innovative technique is proposed for the generation of mother wavelet. The mother wavelet is separately generated for each word utterance. This generates a multidimensional space for speech words and increases the recognition accuracy. The wavelet transform (WT) coefficients are evaluated with respect to the generated mother wavelet for each word utterance and are stored as template along with the generated mother wavelet for each word utterance. The data base consists of 30 word utterances recorded locally using the sound recorder facility. In the recognition mode, the external word utterance is scanned and is divided into PS segments. The trajectory of second LPC is tracked. WT coefficients are evaluated with respect to the mother wavelet of each word in the vocabulary and are compared with the template for each word. The results indicate 100% recognition accuracy.

PS-ZCPA Based Feature Extraction with Auditory Masking, Modulation Enhancement and Noise Reduction for Robust ASR

A pitch-synchronous (PS) auditory feature extraction method based on ZCPA (Zero-Crossings Peak-Amplitudes) was proposed previously and showed more robustness over a conventional ZCPA and MFCC based features. In this paper, firstly, a non-linear adaptive threshold adjustment procedure is introduced into the PS-ZCPA method to get optimal results in noisy conditions with different signal-to-noise ratio (SNR). Next, auditory masking, a well-known auditory perception, and modulation enhancement that simulates a strong relationship between modulation spectrums and intelligibility of speech are embedded into the PS-ZCPA method. Finally, a Wiener filter based noise reduction procedure is integrated into the method to make it more noise-robust, and the performance is evaluated against ETSI ES202 (WI008), which is a standard front-end for distributed speech recognition. All the experiments were carried out on Aurora-2J database. The experimental results demonstrated improved performance of the PS-ZCPA method by embedding auditory masking into it, and a slightly improved performance by using modulation enhancement. The PS-ZCPA method with Wiener filter based noise reduction also showed better performance than ETSI ES202 (WI008).

Pitch synchronous innovation code excited linear prediction (PSI-CELP)

This paper proposes a new speech coding method pitch synchronous innovation code excited linear predictor (PSI-CELP). This method is based on CELP but adds pitch synchronous innovation. This results in even random codevectors being adaptively converted to have pitch periodicity for voiced frames. This scheme can improve the synthesized speech quality of voiced frames in the low bit-rate CELP without increasing either computational complexity or bit rate. In addition to pitch synchronous innovation, this paper also proposes four other methods in which the quality of synthesized speech is effectively improved or the computational complexity is reduced for low bit-rate CELP: (1) the perceptual weighting filter is an MA-type and uses nonquantized LPC parameters; (2) the fixed codebook is prepared as part of the adaptive codebook for nonperiodic frames; (3) the random codebook consists of two-channel conjugate sub-codebooks; and (4) codebook searches are made using delayed decision. In a speech coding system with pitch synchronization of random codevectors, improvements in ratio SNR, segmental SNR, and opinion equivalent Q value are respectively 1.6 dB, 1.0 dB, and 0.5 dB. These basic methods were adopted in the standard codec for Japanese half-rate digital mobile telephone service.

Electronic musical instrument with digital filter

A pitch synchronizing signal snychronized with the pitch of a digital tone signal to be filtered is generated by a pitch synchronizing signal generation circuit. A digital filter circuit which receives the digital tone signal and imparts it with a desired tone color by subjecting it to a proper filter operation executes this filter operation with a sampling period synchronized with the pitch synchronizing signal. A moving formant thereby is realized which is suitable for control of a tone. A pitch synchronization output circuit for sampling and outputting the output of the digital filter circuit in accordance with the pitch synchronizing signal may be provided and this will prevent occurrence of a sampling noise. A switching circuit is provided for enabling switching order of the digital filter circuit between an even number and an odd number. By this switching of order, a desired filter characteristic can be realized with high fidelity. The filter coefficient may be used commonly for two orders positioned at symmetrical positions. Filter coefficients which do not undergo timewise change and those which undergo timewise change may be selectively supplied in separate channels.

Speech analysis homomorphic prediction

Linear prediction is a generally accepted method for obtaining all-pole speech representations. However, in many situations (e.g., nasalization studies) spectral zeros are important and a more general modeling procedure is required. Unfortunately, the need for pitch synchronization has limited the success of available techniques. This paper explores a novel approach to pole-zero analysis, called homomorphic prediction, which seems to avoid the synchronization problem. A minimum-phase estimate of the vocal-tract impluse response is obtained by homomorphic filtering of the speech waveform. Such a signal, by definition, has a known time registration. Linear prediction is applied to this waveform to identify its poles. The LPC residual (error signal) is computed by filtering. This signal contains the information about the zeros. Its z transform is then approximated by a polynomial either through a weighted least squares procedure (homomorphic prediction, using Shanks' method of finding zeros), or by spectral inversion followed by a second pass of LPC (homomorphic prediction involving inverse LPC). Results of a preliminary evaluation on real and synthetic speech are presented.

Speech analysis by homomorphonic prediction

Linear prediction (LPC) is a generally accepted method for obtaining all-pole speech representations. However, in many situations (e.g., nasalization studies) spectral zeros are important and a more general modeling procedure is required. Unfortunately the need for pitch synchronization has limited the success of available techniques. This talk deals with a new approach to pole-zero identification, based on homomorphic prediction, which avoids the synchronization problem. Homomorphonic prediction is a three step process. Homomorphic deconvolution is used to obtain a minimum-phase estimate of the vocal tract impulse response. Such a signal by definition is properly time synchronized. Linear prediction is applied to this waveform to identify its poles. Next, the LPC “residual” (error signal) is computed by inverse filtering. This signal contains the information about the zeros. Its z transform is approximated by a polynomial either through a weighted least-squares procedure (as in Shanks' method) or by spectral inversion followed by a second evaluation on real speech data will be presented. [Supported in part by ARPA, NSF, and the Fannie and John Hertz Fonudation.]