Speech enhancement by harmonic modeling via map pitch tracking

Tabrikian, Joseph; Dubnov, Shlomo; Dickalov, Yulya

doi:10.1109/icassp.2002.5743776

Cited by 6 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11 and it is clearly observed that the proposed PEA performs better than the DHM. Finally, in Table 7 a performance comparison of the proposed EMD based method with DHM, pitch estimator via signal reshaping technique is made with the Xwaves (Talkin 1995), DLFT (Tabrikian et al 2002;Wang and Seneff 2000), and conventional NACF for 'clearly voiced' reference frames is presented. The results for Xwaves and DLFT as reported in Kasi and Zahorian (2002) are obtained at SNR = ∞, i.e., for no noise case.…”

Section: Resultsmentioning

confidence: 99%

Harmonic modification and data adaptive filtering based approach to robust pitch estimation

Roy

Molla

Hirose

et al. 2011

Int J Speech Technol

View full text Add to dashboard Cite

A novel and robust pitch estimation method is presented in this paper. The basic idea is to reshape the speech signal using a combination of the dominant harmonic modification (DHM) and data adaptive time domain filtering techniques. The noisy speech signal is filtered within the ranges of fundamental frequencies to obtain the pre-filtered signal (PFS). The dominant harmonic (DH) of the PFS is determined and enhanced its amplitude. Normalized autocorrelation function (NACF) is applied to that modified signal. Then empirical mode decomposition (EMD) based data adaptive time domain filtering is applied to the NACF signal. Partial reconstruction is performed in EMD domain. The pitch period is determined from the partially reconstructed signal. The experimental results show that the proposed method performs better than the other recently developed methods for noisy and clean speech signals in terms of gross and fine pitch errors.

show abstract

Section: Resultsmentioning

confidence: 99%

Harmonic modification and data adaptive filtering based approach to robust pitch estimation

Roy

Molla

Hirose

et al. 2011

Int J Speech Technol

View full text Add to dashboard Cite

show abstract

“…3.2, we implemented the spectral distribution model described in [16]. This model assumes that the harmonics of the signal are contaminated with noise whose mean energy is independent of the energy of the harmonics.…”

Section: Resultsmentioning

confidence: 99%

“…These models typically assume that the musical signal is contaminated with white noise whose energy is statistically independent of the signal. See for instance [16] and the references therein. In contrast, we assume that there is a leading instrument, or soloist, that is accompanied by an orchestra or a chorus.…”

Section: Spectral Distribution Modelmentioning

confidence: 99%

“…Our starting point is similar to the model presented in [16]. We assume that a note with pitch pi attains high energy at frequencies which are multiples of pi, namely at pih for integer h. These frequencies are often referred to as harmonics.…”

Section: Spectral Distribution Modelmentioning

confidence: 99%

“…In addition, we also describe a simple probabilistic spectral distribution model that is robust to the masking noise of the accompanying instruments and singers. This spectral distribution model is a variant of the harmonic likelihood model for pitch detection [16]. Combining the temporal and spectral probabilistic components, we obtain a joint model which can be thought of as a dynamic Bayesian network [8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust temporal and spectral modeling for query By melody

Shalev‐Shwartz

Dubnov

Friedman

et al. 2002

Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

Query by melody is the problem of retrieving musical performances from melodies. Retrieval of real performances is complicated due to the large number of variations in performing a melody and the presence of colored accompaniment noise. We describe a simple yet effective probabilistic model for this task. We describe a generative model that is rich enough to capture the spectral and temporal variations of musical performances and allows for tractable melody retrieval. While most of previous studies on music retrieval from melodies were performed with either symbolic (e.g. MIDI) data or with monophonic (single instrument) performances, we performed experiments in retrieving live and studio recordings of operas that contain a leading vocalist and rich instrumental accompaniment. Our results show that the probabilistic approach we propose is effective and can be scaled to massive datasets.

show abstract

Noise-Robust Pitch Detection using Auto-correlation Function with Enhancements

Muhammad

2010

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

Speech enhancement by harmonic modeling via map pitch tracking

Cited by 6 publications

References 5 publications

Harmonic modification and data adaptive filtering based approach to robust pitch estimation

Harmonic modification and data adaptive filtering based approach to robust pitch estimation

Robust temporal and spectral modeling for query By melody

Noise-Robust Pitch Detection using Auto-correlation Function with Enhancements

Contact Info

Product

Resources

About