The Iroquois model: using temporal dynamics to separate speakers
نویسندگان
چکیده
We describe a system that can separate and recognize the simultaneous speech of two speakers from a single channel recording and compare the performance of the system to that of human subjects. The system, which we call Iroquois, uses models of dynamics to achieve performance near that of human listeners. However the system exhibits a pattern of performance across conditions that is different from that of human subjects. In conditions where the amplitude of the speakers is similar, the Iroquois model surpasses human performance by over 50%. We hypothesize that the system accomplishes this remarkable feat by employing a different strategy to that of the human auditory system.
منابع مشابه
Super-human multi-talker speech recognition: the IBM 2006 speech separation challenge system
We describe a system for model based speech separation which achieves super-human recognition performance when two talkers speak at similar levels. The system can separate the speech of two speakers from a single channel recording with remarkable results. It incorporates a novel method for performing two-talker speaker identification and gain estimation. We extend the method of model based high...
متن کاملIdentification of the vertebrate Iroquois homeobox gene family with overlapping expression during early development of the nervous system
In Drosophila the decision processes between the neural and epidermal fate for equipotent ectodermal cells depend on the activity of proneural genes. Members of the Drosophila Iroquois-Complex (Iro-C) positively regulate the activity of certain proneural AS-C genes during the formation of external sensory organs. We have identified and characterized three mouse Iroquois-related genes: Irx1, -2 ...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کاملHydrodynamics and water quality assessment of a coastal lagoon using environmental fluid dynamics code explorer modeling system
Ciénaga de Mallorquín is a coastal lagoon designated as a RAMSAR site due to its ecological regional and international importance. In this work, the environmental fluid dynamics code explorer modeling system was implemented to determine the spatio-temporal distribution of temperature, dissolved oxygen, chemical oxygen demand and nutrient levels, and assess the trophic status of Ciénaga de Mallo...
متن کاملProvide a Model for Shaping the Subject in Comparative Studies and Research in the Field of Art With Emphasis on Interdisciplinary Studies
Consideration of comparative research as a "separate and different research process" is an issue that has not been addressed thoroughly, at least in Iran, and few of the research conducted under the title of "comparative" refer to studies conducted using different methods than the usual research methods. On the other hand, there has been a rise in the importance of interaction between different...
متن کامل