Resources

Formant Prediction from MFCC Vectors (Robust 2004)

This work proposes a novel method of predicting formant frequencies from a stream of mel-frequency cepstral coefficients (MFCC) feature vectors. Prediction is based on modelling the joint density of MFCC vectors and formant vectors using a Gaussian mixture model (GMM). Using this GMM and an input MFCC vector, two maximum a posteriori (MAP) prediction methods are developed. The first method predicts formants from the closest, in some sense, cluster to the input MFCC vector, while the second method takes a weighted contribution of formants from all clusters. Experimental results are presented using the ETSI Aurora connected digit database and show that the predicted formant frequency is within 3.25% of the reference formant frequency, as measured from hand-corrected formant tracks.

Predicting Formant Frequencies from MFCC Vectors (ICASSP 2005)

This work proposes a novel method of predicting formant frequencies from a stream of mel-frequency cepstral coefficients (MFCC) feature vectors. Prediction is based on modelling the joint density of MFCCs and formant frequencies using a Gaussian mixture model (GMM). Using this GMM and an input MFCC vector, two maximum a posteriori (MAP) prediction methods are developed. The first method predicts formants from the closest, in some sense, cluster to the input MFCC vector, while the second method takes a weighted contribution of formants predicted from all clusters. Experimental results are presented using the ETSI Aurora connected digit database and show that predicted formant frequencies are within 3.2% of reference formant frequencies.

Formant Frequency Prediction from MFCC Vectors in Noisy Environments (Interspeech 2005)

This paper proposes a method of predicting the formant frequencies of a frame of speech from its mel-frequency cepstral coefficient (MFCC) representation. Prediction is achieved through the creation of a Gaussian mixture model (GMM) which models the joint density of formant frequencies and MFCCs. Using this GMM and an input MFCC vector, a maximum a posteriori (MAP) prediction of the formant frequencies is generated. Formant prediction accuracy is evaluated on both a constrained vocabulary connected digits database and on a 5000 word large vocabulary database. Experiments first examine the accuracy of formant frequency prediction as the number of clusters in the GMM is varied with a best formant frequency prediction error of 3.72% being obtained. Secondly the effect of noise on formant prediction accuracy is examined. A fall in accuracy is observed with reducing signal-to-noise ratios, but by using a GMM matched to the noise conditions formant prediction accuracy is significantly improved.

Prediction of Voicing Class and Formant Frequencies from MFCC Vectors in Noise

HMM-based MAP Prediction of Voiced and Unvoiced Formant Frequencies from Noisy MFCC Vectors

This paper describes how formant frequencies of voiced and unvoiced speech can be predicted from mel-frequency cepstral coefficients (MFCC) vectors using maximum a posteriori (MAP) estimation within a hidden Markov model (HMM) framework. Gaussian mixture models (GMMs) are used to model the local joint density of MFCCs and formant frequencies. More localised prediction is achieved by modelling speech using voiced, unvoiced and non-speech GMMs for every state of each model of a set of HMMs. To predict formant frequencies from a MFCC vector, first a prediction of the speech class (voiced, unvoiced or non-speech) is made. Formant frequencies are predicted from voiced and unvoiced speech using a MAP estimation made using the state-specific GMMs. This 'HMM-GMM' prediction of speech class and formant frequencies was evaluated on a male 5000 word unconstrained large vocabulary speaker-independent database.

MAP Prediction of Formant Frequencies and Voicing Class from MFCC Vectors in Noise

Accepted for Publication, Speech Communication 2006.

Novel methods are presented for predicting formant frequencies and voicing class from mel-frequency cepstral coefficients (MFCCs). It is shown how Gaussian mixture models (GMMs) can be used to model the relationship between formant frequencies and MFCCs. Using such models and an input MFCC vector, a maximum a posteriori (MAP) prediction of formant frequencies can be made. The specific relationship each speech sound has between MFCCs and formant frequencies is exploited by using state-specific GMMs within a framework of a set of hidden Markov models (HMMs). Formant prediction accuracy and voicing prediction of speaker-independent male speech are evaluated on both a constrained vocabulary connected digits database and a large vocabulary database. Experimental results show that for HMM-GMM prediction on the connected digits database, voicing class prediction error is less than 3.5%. Less than 1.8% of frames have formant frequency percentage errors greater than 20% and the mean percentage error of the remaining frames is less than 3.7%. Further experiments show prediction accuracy under noisy conditions. For example, at a signal-to-noise ratio (SNR) of 0dB, voicing class prediction error increases to 9.4%, less than 4.3% of frames have formant frequency percentage errors over 20% and the formant frequency percentage error for the remaining frames is less than 5.7%.

Research Team

Dr. Ben Milner, Mr. Jonathan Darch