Lyon’s Auditory Model Inversion: a Tool for Sound Separation and Speech Enhancement
نویسندگان
چکیده
A new implementation of Lyon’s Auditory Model and an optimised inversion procedure will be presented. Both the passive and active Lyon’s cochlea models were studied as new signal processing analysis schemes, while only the first one was considered regarding the inversion procedure. Following the work of M. Slaney, sound resynthesis was obtained inverting the correlogram representation by a new optimised algorithm. The utility of auditory model inversion will be emphasised focusing on the problem of speech enhancement and sound separation.
منابع مشابه
Single-Microphone Speech Separation: The use of Speech Models
Separation of speech sources is fundamental for robust communication. In daily conversations, signals reaching our ears generally consist of target speech sources, interference signals from competing speakers and ambient noise. Take an example, talking with someone in a cocktail party and making a phone call in a train compartment. Fig. 1 shows a typical indoor environment having multiple sound...
متن کاملAuditory Fovea Based Speech Enhancement and Its Application to Dialog System
Robots, in particular, mobile robots should listen to and recognize speeches with their own ears in a real world to attain smooth communications with people. This paper presents an active direction-pass filter (ADPF) that separates sounds originating from the specified direction by using a pair of microphones. Its application to front-end processing for speech recognition is also reported. Sinc...
متن کاملAuditory model inversion for sound separation
1 Techniques to recreate sounds from perceptual displays known as cochleagrams and correlograms are developed using a convex projection framework. Prior work on cochlear-model inversion is extended to account for rectiÞcation and gain adaptation. A prior technique for phase recovery in spectrogram inversion is combined with the synchronized overlap-and-add technique of speech rate modiÞcation, ...
متن کاملBayesian Extension of MUSIC for Sound Source Localization and Tracking
This paper presents a Bayesian extension of MUSIC-based sound source localization (SSL) and tracking method. SSL is important for distant speech enhancement and simultaneous speech separation for improving speech recognition, as well as for auditory scene analysis by mobile robots. One of the drawbacks of existing SSLmethods is the necessity of careful parameter tunings, e.g., the sound source ...
متن کاملSpeech Enhancement from Interfering Sounds Using Casa Techniques and Blind Source Separation
In this paper we propose novel biologically plausible model for segregation of one dominant speaker from the other concurrent speakers and environmental noise in real cocktailparty scenario. The developed method integrates two powerful techniques: computational scene analysis (CASA) and blind source separation (BSS) technique with bandpass preprocessing. Since each of these techniques applied a...
متن کامل