Source Separation with One Ear: Proposition for an Anthropomorphic Approach
- PDF / 1,092,114 Bytes
- 9 Pages / 600 x 792 pts Page_size
- 74 Downloads / 212 Views
Source Separation with One Ear: Proposition for an Anthropomorphic Approach Jean Rouat ´ D´epartement de G´enie Electrique et de G´enie Informatique, Universit´e Sherbrooke, 2500 boulevard de l’Universit´e, Sherbrooke, QC, Canada J1K 2R1 ´ Equipe de Recherche en Micro-´electronique et Traitement Informatique des Signaux (ETMETIS), D´epartement de Sciences Appliqu´es, Universit´e du Qu´ebec a` Chicoutimi, 555 boulevard de l’Universit´e, Chicoutimi, Qu´ebec, Canada G7H 2B1 Email: [email protected]
Ramin Pichevar ´ D´epartement de G´enie Electrique et de G´enie Informatique, Universit´e Sherbrooke, 2500 boulevard de l’Universit´e, Sherbrooke, QC, Canada J1K 2R1 Email: [email protected] ´ Equipe de Recherche en Micro-´electronique et Traitement Informatique des Signaux (ETMETIS), D´epartement de Sciences Appliqu´es, Universit´e du Qu´ebec a` Chicoutimi, 555 boulevard de l’Universit´e, Chicoutimi, Qu´ebec, Canada G7H 2B1 Received 9 December 2003; Revised 23 August 2004 We present an example of an anthropomorphic approach, in which auditory-based cues are combined with temporal correlation to implement a source separation system. The auditory features are based on spectral amplitude modulation and energy information obtained through 256 cochlear filters. Segmentation and binding of auditory objects are performed with a two-layered spiking neural network. The first layer performs the segmentation of the auditory images into objects, while the second layer binds the auditory objects belonging to the same source. The binding is further used to generate a mask (binary gain) to suppress the undesired sources from the original signal. Results are presented for a double-voiced (2 speakers) speech segment and for sentences corrupted with different noise sources. Comparative results are also given using PESQ (perceptual evaluation of speech quality) scores. The spiking neural network is fully adaptive and unsupervised. Keywords and phrases: auditory modeling, source separation, amplitude modulation, auditory scene analysis, spiking neurons, temporal correlation.
1.
INTRODUCTION
1.1. Source separation Source separation of mixed signals is an important problem with many applications in the context of audio processing. It can be used to assist robots in segregating multiple speakers, to ease the automatic transcription of videos via the audio tracks, to segregate musical instruments before automatic transcription, to clean up signal before performing speech recognition, and so forth. The ideal instrumental setup is based on the use of arrays of microphones during recording to obtain many audio channels. In many situations, only one channel is available to the audio engineer that still has to solve the separation problem. Most monophonic source separation systems require a priori knowledge, that is, expert systems (explicit knowledge) or statistical approaches (implicit knowledge) [1]. Most of these systems perform reasonably well only on specific signals (generally voiced speech or harmonic music) and fail
to efficient
Data Loading...