Abstract
Digital hearing aids impose strong complexity and memory constraints on digital signal processing algorithms that implement different applications. This paper proposes a low complexity approach for automatic sound classification in digital hearing aids. The proposed scheme, which operates on a frame-by-frame basis, consists of two stages: analysis stage and classification stage. The analysis stage provides a set of low-complexity signal features derived from fundamental frequency (F0) estimation. Here, F0 estimation is performed by a decimated difference function, which results in a reduced-complexity analysis stage. The classification stage has been designed with the aim of reducing the complexity while maintaining high accuracy rates. Three low-complexity classifiers have been evaluated (tree-based C4.5, 1-Nearest Neighbor (1-NN) and a Multilayer Perceptron (MLP)), the MLP being chosen because it provides the best accuracy rates and fits to the computational and memory constraints of ultra low-power DSP-based hearing aids. The classification stage is composed of a MLP classifier followed by a Hidden Markov Model (HMM), providing a good trade-off solution between complexity and classification accuracy rate. The goal of the proposed approach is to perform a robust discrimination among speech/nonspeech parts of audio signals in commercial digital hearing aids, the computational cost being a critical issue. For the experiments, an audio database including speech, music and noise signals has been used.
Similar content being viewed by others
References
Alexandre E, Cuadra L, Alvarez L, Rosa-Zurera M (2007) NN-based automatic sound classifier for digital hearing aids. In: IEEE Int. Symposium on Intelligent Signal Processing. Alcala de Henares, Spain
Alexandre E, Cuadra L, Alvarez L, Utrilla M (2007) Exploring the feasibility of a two-layer NN-based sound classifier for hearing aids. In: Proc. EUSIPCO 2007, Poznań, Poland, 3–7 September 2007
Alexandre E, Cuadra L, Rosa M, Lopez-Ferreras F (2007) Feature selection for sound classification in hearing aids through restricted search driven by genetic algorithms. IEEE Trans Audio, Speech and Languagge Processing 15(8):2249–2256
Alexandre E, Cuadra L, Rosa M, López-Ferreras F (2008) Speech/nonspeech classification in hearing aids driven by tailored neural networks. In: Prasad B, Prassana SM (eds) Speech, audio, image and biomedical signal processing using neural networks. Springer, Berlin, pp 145–167
Alexandre E, Rosa-Zurera M, Cuadra L, Gil-Pita R (2006) Application of fisher linear discriminant analysis to speech/music classification. In: Proceedings of the 120th audio engineering society convention, vol 2. Paris, France, pp 1666–1669
Benesty J, Makino S, Chen J (2005) Speech enhancement. Springer, Berlin, ISBN 354024039X
Büchler M (2002) Algorithms for sound classification in hearing instruments. PhD Thesis, Swiss Federal Institute of Technology, Zurich
Büchler M, Allegro S, Launer S, Dillier N (2005) Sound classification in hearing aids inspired by auditory scene analysis. EURASIP J Appl Signal Process 18:2991–3002
Chang WC, Alvin Su WY, Chunghsin Y, Roebel A, Rodet X (2008) Multiple-F0 tracking based on a high-order HMM model. In: Proc. of the 11th int. conference on digital audio effects (DAFx-08), Espoo, Finland, 1–4 September 2008
Cheveigne A, Kawahara H (2002) YIN, a fundamental frequency estimator for speech and music. J Acoust Soc Am (JASA) 111(4):1917–1930
Cuadra L, Alexandre E, Gil-Pita R, Vicen R, Álvarez L (2009) Influence of acoustic feedback on the learning strategies of neural network-based sound classifiers in digital hearing aids. EURASIP J Appl Signal Process. doi:10.1155/2009/465189
Dong R, Hermann D, Cornu E, Chau E (2007) Low-power implementation of an HMM-based sound environment classification algorithm for hearing aid application. Proc. EUSIPCO 2007, Poznań, Poland, 3–7 September 2007
El-Maleh K, Klein M, Petrucci G, Kabal P (2000) Speech/music discrimination for multimedia applications. In: Proc. IEEE ICASSP’2000, vol 6, pp 2445–2448
Gil-Pita R, Alexandre E, Cuadra L, Vicen R, Rosa-Zurera M (2009) Analysis of the effects of finite precision in neural network-based sound classifiers for digital hearing aids. EURASIP J Appl Signal Process. doi:10.1155/2009/456945
Harb H, Chen L (2003) Robust speech music discrimination using spectrum’s first order statistics and neural networks. In: Proc. IEEE int. symp. on signal processing and its applications, vol 2. pp 125–128
Keidser G (1995) The relationships between listening conditions and alterative amplification schemes for multiple memory hearing aids. Ear Hear 16:575–586
Keidser G (1996) Selecting different amplification for different listening conditions. J Am Acad Audiol 7:92–104
Klapuri A (2003) Multiple fundamental frequency estimation by harmonicity and spectral smoothness. IEEE Trans Speech Audio Process 11(6):804–816
Klapuri A (2008) Multipitch analysis of polyphonic music and speech signals using an auditory model. IEEE Trans. Audio, Speech and Language Processing 16(2):255–266
Le Roux J, Kameoka H, Ono N, de Cheveigne A, Sagayama S (2007) Single and multiple F 0 contour estimation through parametric spectrogram modeling of speech in noisy environments. IEEE Transactions on Audio, Speech and Language Processing 15(4):1135–1145
Luo F, Nehorai A (2006) Recent developments in signal processing for digital hearing aids. IEEE Signal Process Mag 23(5):103–106
Moore BC (1989) An introduction to the psychology of hearing, 3rd edn. Academic, New York
Nordqvist P, Leijon A (2004) An efficient robust sound classification algorithm for hearing aids. J Acoust Soc Am 115(6):3033–3041
On Semiconductor (2004) Toccata plus flexible DSP system for hearing aids. http://www.amis.com/products/dsp/toccata_plus.html
On Semiconductor (2010) http://www.onsemi.com
Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers
Quinlan JR (1996) Improved use of continuous attributes in C4.5. J Artif Intell Res 4:77–90
Rabiner LR (1989) A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286
Rabiner LR, Juang BH (1986) An introduction to hidden Markov models. IEEE ASSP Mag 3(1):4–16
Rohdenburg T, Hohmann V, Kollmeier B (2007) Robustness analysis of binaural hearing aid beamformer algorithms by means of objective perceptual quality measures. In: IEEE workshop on applications of signal processing to audio and acoustics. New Paltz, NY, USA, 21–24 October 2007
Ruiz-Reyes N, Vera-Candeas P, Muñoz JE, Garca-Galán S, Cañadas FJ (2009) New speech/music discrimination approach based on fundamental frequency estimation. Multimedia Tools and Applications, vol 41. Springer, pp 253–286
Scheirer E, Slaney M (1997) Construction and evaluation of a robust multifeature speech/music discriminator. In: Proc. IEEE ICASSP’97. Munich, Germany, pp 1331–1334
Vera-Candeas P, Cañadas-Quesada FJ, Alexandre E, Rosa M, Ruiz-Reyes N (2008) Musical-inspired features for automatic sound classification in digital hearing aids. In: 124th Audio Engineering Society Convention, Amsterdam, The Netherlands
Acknowledgements
This work was supported by FEDER, the Spanish Ministry of Education and Science under Project TEC2006-13883-C04-03 and the Andalusian Council under project P07-TIC-02713. We would like to thank E. Alexandre for sharing with us the database designed for digital hearing aid applications.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cabañas Molero, P., Ruiz Reyes, N., Vera Candeas, P. et al. Low-complexity F0-based speech/nonspeech discrimination approach for digital hearing aids. Multimed Tools Appl 54, 291–319 (2011). https://doi.org/10.1007/s11042-010-0523-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-010-0523-1