The paper deals with the use of formant features in dynamic time warping based speech recognition. These features can be simply visualized and give a new insight into understanding the reasons of speech recognition errors. The formant feature extraction method, based on the singular prediction polynomials, has been applied in recognition of isolated words. However, the speech recognition performance depends on the order of singular prediction polynomials, whether symmetric or antisymmetric singular prediction polynomials are used for recognition and as well on the fact even or odd order of these polynomials is chosen. Also, it is important to know how informative separate formants are, how the speech recognition results depend on other parameters of the recognition system such as: analysis frame length, number of the formants used in recognition, frequency scale used for representation of formant features, and the preemphasis filter parameters. Properly choosing the processing parameters, it is possible to optimize the speech recognition performance.
The aim of our current investigation is to optimize formant feature based isolated word recognition performance by varying processing parameters of the recognition system as well as to find improvements of the recognition system which could make it more robust to white noise. The optimization experiments were carried out using speech records of 111 Lithuanian words. The speech signals were recorded in the conventional room environment (SNR = 30 dB). Then the white noise was generated at a predefined level (65 dB, 60 dB and 55 dB) and added to the test utterances. The recognition performance was evaluated at various noise levels.
The optimization experiments allowed us to improve considerably the performance of the formant feature based speech recognition system and made the system more robust to white noise.
[1]
Samy Bengio,et al.
HMM2- Extraction of Formant Features and their Use for Robust ASR
,
2001
.
[2]
S.M. Kay,et al.
Spectrum analysis—A modern perspective
,
1981,
Proceedings of the IEEE.
[3]
古井 貞煕,et al.
Digital speech processing, synthesis, and recognition
,
1989
.
[4]
Sadaoki Furui,et al.
Digital Speech Processing, Synthesis, and Recognition
,
1989
.
[5]
Samy Bengio,et al.
HMM2- extraction of formant structures and their use for robust ASR
,
2001,
INTERSPEECH.
[6]
L. F. Willems,et al.
Robust formant analysis for speech synthesis applications
,
1987,
ECST.
[7]
L. Marple.
A new autoregressive spectrum analysis algorithm
,
1980
.
[8]
T.H. Crystal,et al.
Linear prediction of speech
,
1977,
Proceedings of the IEEE.
[9]
Philippe Delsarte,et al.
The split Levinson algorithm
,
1986,
IEEE Trans. Acoust. Speech Signal Process..
[10]
Philippe Delsarte,et al.
On the splitting of classical algorithms in linear prediction theory
,
1987,
IEEE Trans. Acoust. Speech Signal Process..
[11]
Algirdas Bastys,et al.
The Use of Group Delay Features of Linear Prediction Model for Speaker Recognition
,
2010,
Informatica.
[12]
Antanas Lipeika,et al.
On the Use of the Formant Features in the Dynamic Time Warping Based Recognition of Isolated Words
,
2008,
Informatica.
[13]
Samy Bengio,et al.
Evaluation of formant-like features on an automatic vowel classification task.
,
2004,
The Journal of the Acoustical Society of America.
[14]
Hermann Ney,et al.
Formant estimation for speech recognition
,
1998,
IEEE Trans. Speech Audio Process..
[15]
Peter Kabal,et al.
The computation of line spectral frequencies using Chebyshev polynomials
,
1986,
IEEE Trans. Acoust. Speech Signal Process..