ALTIS: A new algorithm for adaptive long-term SNR estimation in multi-talker babble. (November 2019)

• Record Type: Journal Article
• Authors: Soleymani, Roozbeh; Selesnick, Ivan W.; Landsberger, David M.
• Is Part Of: Computer speech & language. Volume 58(2019)
• Page Start: 231
• Page End: 246
• Publication Date: 2019-11
• Subjects: Multi-talker babble -- Long-term SNR -- Adaptive SNR -- Real-time SNR -- Signal-to-noise ratio; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2019.05.001
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A real-time SNR estimation algorithm is introduced. The algorithm is specifically designed for speech in multi-talker babble. The algorithm is calibrated to be insensitive to short-term SNR fluctuations. The algorithm quickly responds to non-transient changes in instantaneous SNR. Abstract: We introduce a real-time capable algorithm which estimates the long-term signal to noise ratio (SNR) of the speech in multi-talker babble noise. In real-time applications, long-term SNR is calculated over a sufficiently long moving frame of the noisy speech ending at the current time. The algorithm performs the real-time long-term SNR estimation by averaging "speech-likeness" values of multiple consecutive short-frames of the noisy speech which collectively form a long-frame with an adaptive length. The algorithm is calibrated to be insensitive to short-term fluctuations and transient changes in speech or noise level. However, it quickly responds to non-transient changes in long-term SNR by adjusting the duration of the long-frame on which the long-term SNR is measured. This ability is obtained by employing an event detector and adaptive frame duration. The event detector identifies non-transient changes of the long-term SNR and optimizes the duration of the long-frame accordingly. The algorithm was trained and tested for randomly generated speech samples corrupted with multi-talker babble. In addition to its ability to provide an adaptive long-term SNR estimation in a dynamic noisy situation, the evaluation results show that the algorithm outperforms the existing overall SNR estimation methods in multi-talker babble over a wide range of number of talkers and SNRs. The relatively low computational cost and the ability to update the estimated long-term SNR several times per second make this algorithm capable of operating in real-time speech processing applications.