Singing Voice Analysis Research Articles

Determination of the vocal tract model order in iterative adaptive inverse filtering

This paper is part of a special issue on Music Technology. Accurate estimation of glottal wave is an important method for singing voice analysis via voicing patterns. In this paper, an optimising method is proposed for automatic determination of vocal tract linear prediction analysis order that follows the specific situation of different voicing scenes based on Iterative Adaptive Inverse Filtering (IAIF) aiming at getting a more accurate glottal wave from speech or singing voice signal in a non-invasive way. In comparison with existing methods that use fixed experience order, the proposed method can achieve up to 8.41% improvement in correlation coefficient with the real glottal wave.

Towards a Singing Voice Multi-Sensor Analysis Tool: System Design, and Assessment Based on Vocal Breathiness.

Singing voice is a human quality that requires the precise coordination of numerous kinetic functions and results in a perceptually variable auditory outcome. The use of multi-sensor systems can facilitate the study of correlations between the vocal mechanism kinetic functions and the voice output. This is directly relevant to vocal education, rehabilitation, and prevention of vocal health issues in educators; professionals; and students of singing, music, and acting. In this work, we present the initial design of a modular multi-sensor system for singing voice analysis, and describe its first assessment experiment on the ‘vocal breathiness’ qualitative characteristic. A system case study with two professional singers was conducted, utilizing signals from four sensors. Participants sung a protocol of vocal trials in various degrees of intended vocal breathiness. Their (i) vocal output, (ii) phonatory function, and (iii) respiratory behavior-per-condition were recorded through a condenser microphone (CM), an Electroglottograph (EGG), and thoracic and abdominal respiratory effort transducers (RET), respectively. Participants’ individual respiratory management strategies were studied through qualitative analysis of RET data. Microphone audio samples breathiness degree was rated perceptually, and correlation analysis was performed between sample ratings and parameters extracted from CM and EGG data. Smoothed Cepstral Peak Prominence (CPPS) and vocal folds’ Open Quotient (OQ), as computed with the Howard method (HOQ), demonstrated the higher correlation coefficients, when analyzed individually. DECOM method-computed OQ (DOQ) was also examined. Interestingly, the correlation coefficient of pitch difference between estimates from CM and EGG signals appeared to be (based on the Pearson correlation coefficient) statistically insignificant (a result that warrants investigation in larger populations). The study of multi-variate models revealed even higher correlation coefficients. Models studied were the Acoustic Breathiness Index (ABI) and the proposed multiple regression model CDH (CPPS, DOQ, and HOQ), which was attempted in order to combine analysis results from microphone and EGG signals. The model combination of ABI and the proposed CDH appeared to yield the highest correlation with perceptual breathiness ratings. Study results suggest potential for the use of a completed system version in vocal pedagogy and research, as the case study indicated system practicality, a number of pertinent correlations, and introduced topics with further research possibilities.

BioVoice: A multipurpose tool for voice analysis

ObjectiveThis paper introduces BioVoice, a user-friendly software tool for the acoustical analysis of the human voice. It estimates more than 20 acoustical parameters with advanced and robust analysis techniques specifically developed for different vocal emissions, from the newborn to the adult and the singer. MethodsBioVoice performs both time and frequency analyses, detecting the number, length, and percentage of voiced and unvoiced segments and computing fundamental frequency (F0), formant frequencies (F1-F3), noise level, and jitter. The software tool computes the melodic shape of F0 out of 12 basic shapes and allows performing perceptual analysis in newborn and child voice. In the singing voice case, formants up to F5 are computed as well as the quality ratio and parameters concerning vibrato and its regularity. Colour figures and Excel tables show F0, the spectrogram with formants, voiced segments, and quality ratio. ResultsExamples of voice analysis in adults, children, newborns, and singers are presented. They show the specific capabilities and the high performance of BioVoice also as compared to another existing software tool. SignificanceBioVoice is a free user-friendly software tool for voice analysis that implements new estimation techniques. Basic parameters are computed as well as new ones specifically developed for newborn cry and singing voice analysis, not available with current software tools. ConclusionsBioVoice is capable to deal with low to high pitched voices implementing dedicated tools. Thanks to its simple and intuitive interface, colour figures and Excel tables, it is a valuable tool suitable also for the inexperienced user.

Robust singer identification of Indian playback singers

Singing voice analysis has been a topic of research to assist several applications in the domain of music information retrieval system. One such major area is singer identification (SID). There has been enormous increase in production of movies and songs in Bollywood industry over the last 50 decades. Surveying this extensive dataset of singers, the paper presents singer identification system for Indian playback singers. Four acoustic features namely—formants, harmonic spectral envelope, vibrato, and timbre—that uniquely describe the singer are extracted from the singing voice segments. Using the combination of these multiple acoustic features, we address the major challenges in SID like the variations in singer’s voice, testing of multilingual songs, and the album effect. Systematic evaluation shows the SID is robust against the variations in singer’s singing style and structure of songs and is effective in identifying the cover songs and singers. The results are investigated on in-house cappella database consisting of 26 singers and 550 songs. By performing dimension reduction of the feature vector and using Support Vector Machine classifier, we achieved an accuracy of 86% using fourfold cross validation process. In addition, performance comparison of the proposed work with other existing approaches reveals the superiority in terms of volume of dataset and song duration.

KaraMIR: A Project for Cover Song Identification and Singing Voice Analysis Using a Karaoke Songs Dataset

We introduce KaraMIR, a musical project dedicated to karaoke song analysis. Within KaraMIR, we define Kara1k, a dataset composed of 1000 cover songs provided by Recisio Karafun application, and the corresponding 1000 songs by the original artists. Kara1k is mainly dedicated toward cover song identification and singing voice analysis. For both tasks, Kara1k offers novel approaches, as each cover song is a studio-recorded song with the same arrangement as the original recording, but with different singers and musicians. Essentia, harmony-analyser, Marsyas, Vamp plugins and YAAFE have been used to extract audio features for each track in Kara1k. We provide metadata such as the title, genre, original artist, year, International Standard Recording Code and the ground truths for the singer’s gender, backing vocals, duets, and lyrics’ language. KaraMIR project focuses on defining new problems and describing features and tools to solve them. We thus provide a comparison of traditional and new features for a cover song identification task using statistical methods, as well as the dynamic time warping method on chroma, MFCC, chords, keys, and chord distance features. A supporting experiment on the singer gender classification task is also proposed. The KaraMIR project website facilitates the continuous research.

Determining the Relevant Criteria for Three-dimensional Vocal Tract Characterization

Soprano singers face a number of specific challenges when singing vowels at high frequencies, due to the wide spacing of harmonics in the voice source. The varied and complex techniques used to overcome these are still not fully understood. Magnetic resonance imaging (MRI) has become increasingly popular in recent years for singing voice analysis. This study proposes a new protocol using three-dimensional MRI to investigate the articulatory parameters relevant to resonance tuning, a technique whereby singers alter their vocal tract to shift its resonances nearer to a voice source harmonic, increasing the amplitude of the sound produced. The protocol was tested with a single soprano opera singer. Drawing on previous MRI studies, articulatory measurements from three-dimensional MRI images were compared to vocal tract resonances measured directly using broadband noise excitation. The suitability of the protocol was assessed using statistical analysis. No clear linear relationships were apparent between articulatory characteristics and vocal tract resonances. The results were highly vowel dependent, showing different patterns of resonance tuning and interactions between variables. This potentially indicates a complex interaction between the vocal tract and sung vowels in soprano voices, meriting further investigation. The effective interpretation of MRI data is essential for a deeper understanding of soprano voice production and, in particular, the phenomenon of resonance tuning. This paper presents a new protocol that contributes toward this aim, and the results suggest that a more vowel-specific approach is necessary in the wider investigation of resonance tuning in female voices.

Singing Voice Separation and Vocal F0 Estimation Based on Mutual Combination of Robust Principal Component Analysis and Subharmonic Summation

This paper presents a new method of singing voice analysis that performs mutually-dependent singing voice separation and vocal fundamental frequency (F0) estimation. Vocal F0 estimation is considered to become easier if singing voices can be separated from a music audio signal, and vocal F0 contours are useful for singing voice separation. This calls for an approach that improves the performance of each of these tasks by using the results of the other. The proposed method first performs robust principal component analysis (RPCA) for roughly extracting singing voices from a target music audio signal. The F0 contour of the main melody is then estimated from the separated singing voices by finding the optimal temporal path over an F0 saliency spectrogram. Finally, the singing voices are separated again more accurately by combining a conventional time-frequency mask given by RPCA with another mask that passes only the harmonic structures of the estimated F0s. Experimental results showed that the proposed method significantly improved the performances of both singing voice separation and vocal F0 estimation. The proposed method also outperformed all the other methods of singing voice separation submitted to an international music analysis competition called MIREX 2014.

Practical determination of acoustic parameters of the singing voice implemented in the interactive analysis software EVOCANTO.

Practical methods of analysis with low computational complexity are presented for the determination of acoustic parameters from radiated sound pressure spectra of sustained sung vowels. Sound spectra are analyzed in order to obtain the fundamental vocal source frequency F0 and its harmonics, the corresponding musical pitch, the first few “formant” frequencies F1, F2, possibly up to F5, that are apparent from the harmonic contour, a nominal vocal tract shape derived from (F1, F2), a measure of formant-to-harmonic tuning of F1 and F2, indication of the presence of a singer’s formant, and a measure of the rate of vibrato. Real-time determination and display of these parameters are integrated into the singing voice analysis software EVOCANTO, a graphical interactive didactic computer program which is intended as a teaching aid for singing tutors and students. Examples of the use of EVOCANTO are presented for typical male and female singing voice registers.

A system for parallel measurement of glottis opening and larynx position

The simultaneous assessment of glottal dynamics and larynx position can be beneficial for the diagnosis of disordered voice or speech production and swallowing. Up to now, methods either concentrate on assessment of the glottis opening using optical, acoustical or electrical (electroglottography, EGG) methods, or on visualisation of the larynx position using ultrasound, computer tomography or magnetic resonance imaging techniques. The method presented here makes use of a time-multiplex measurement approach of space-resolved transfer impedances through the larynx. The fast sequence of measurements allows a quasi simultaneous assessment of both larynx position and EGG signal using up to 32 transmit–receive signal paths. The system assesses the dynamic opening status of the glottis as well as the vertical and back/forward motion of the larynx. Two electrode-arrays are used for the measurement of the electrical transfer impedance through the neck in different directions. From the acquired data the global and individual conductivity is calculated as well as a 2D point spatial representation of the minimum impedance. The position information is shown together with classical EGG signals allowing a synchronous visual assessment of glottal area and larynx position. A first application to singing voice analysis is presented that indicate a high potential of the method for use as a non-invasive tool in the diagnosis of voice, speech, and swallowing disorders.

Inverse filtering in singing voice: a critical analysis

Inverse filtering provides a noninvasive method to extract the voice source, and thus get insight into voice quality. Although this technique is widely used in speech analysis, this is not the case in singing voice, where its use has been even questioned by some authors. In this paper, a comparative study of some representative inverse filtering techniques will be presented in order to identify their main limitations in singing voice analysis. After a rough classification of the inverse filtering techniques, three representative procedures will be selected in order to cover all kind of approaches, and then evaluated taking into account two relevant features: their fundamental frequency limitation, and their sensitivity to the source-tract interaction. To make this comparative study possible, an interactive source-filter model we propose will be used such that the source-tract interaction can be controlled. In this way, the above-mentioned effects will be evaluated based on a simulation analysis, with a realistic singing production model. Natural singing voice results will be also reported to validate the simulations. This study will allow concluding that the main limiting aspect of inverse filtering in singing voice analysis is the fundamental frequency limitation, whereas the source-tract interaction represents a less relevant issue