Journal ArticleDOI
Separation of speech from interfering speech by means of harmonic selection
Reads0
Chats0
TLDR
In this paper, the harmonics of the desired voice in the Fourier transform of the input were selected to distinguish between two different voices. But the authors focus on the principal subproblem, the separation of vocalic speech.Abstract:
A common type of interference in speech transmission is that caused by the speech of a competing talker. Although the brain is adept at clarifying such speech, it relies heavily on binaural data. When voices interfere over a single channel, separation is much more difficult and intelligibility suffers. Clarifying such speech is a complex and varied problem whose nature changes with the moment‐to‐moment variation in the types of sound which interfere. This paper describes an attack on the principal subproblem, the separation of vocalic speech. Separation is done by selecting the harmonics of the desired voice in the Fourier transform of the input. In implementing this process, techniques have been developed for resolving overlapping spectrum components, for determining pitches of both talkers, and for assuring consistent separation. These techniques are described, their performance on test utterances is summarized, and the possibility of using this process as a basis for the solution of the general two‐tal...read more
Citations
More filters
Dissertation
Information theoretic approaches to source separation
TL;DR: Thesis (M.S.)--Massachusetts Institute of Technology, Program in Media Arts & Sciences, 1997.
Proceedings ArticleDOI
Optimal multi-pitch estimation using the EM algorithm for co-channel speech separation
TL;DR: The problem of optimally estimating the pitch of each of several speakers talking simultaneously is addressed and a multipitch model is proposed which is used in conjunction with an EM (expectation maximization)-based iterative estimation scheme, offering improved cochannel speech separation.
Book ChapterDOI
Fundamentals of Noise Reduction
TL;DR: This chapter presents a methodical overview of the state of the art of noise-reduction algorithms, categorized into three fundamental classes: filtering techniques, spectral restoration, and model-based methods.
Journal ArticleDOI
A Maximum Likelihood Estimation of Vocal-Tract-Related Filter Characteristics for Single Channel Speech Separation
TL;DR: A new technique for separating two speech signals from a single recording is presented and effectively adds vocal-tract-related filter characteristics as a new cue to CASA models using a new grouping technique based on an underdetermined blind source separation.
Patent
Single channel sound separation
Les Atlas,Jeffrey M. Thompson +1 more
TL;DR: In this article, a combined audio signal is manipulated using a base acoustic transform, followed by a second modulation transform, which separates the combined signals into distinguishable components, and the components corresponding to the undesired speaker are masked, leaving only the second modulo transform of the desired speaker's audio signal.