Intelligent Systems’ Holistic Evolving Analysis of Real-Life Universal Speaker Characteristics
نویسندگان
چکیده
In this position paper we present the FP7 ERC starting grant project iHEARu (Intelligent systems’ Holistic Evolving Analysis of Real-life Universal speaker characteristics). This project addresses several fundamental shortcomings in state of the art methods for computational paralinguistics, by introducing holistic analysis, evolving learning of features and models, and collection of real-life, large-scale data annotated in multiple dimensions (‘universally’). We discuss the first aspect of the project, holistic analysis, in more detail, and give benchmark results using state of the art multi-target learning methods on the INTERSPEECH 2012 Speaker Trait Challenge dataset (Likability Sub-Challenge). The results clearly indicate the need for improved machine learning methods and data collection to learn holistic speaker classification.
منابع مشابه
Design and Early Simulations of Next Generation Intelligent Energy Systems
The aim of this paper is twofold. Firstly, to briefly present the overall objectives and the expected outcome of an on-going effort concerning the design the implementation and the analysis of next generation intelligent energy systems based on anticipatory control and a set of ICT emerging technologies and innovations. Secondly, to describe an early proof-of-concept implementation and the prel...
متن کاملEvolving Intelligent Systems Selected Topics of Evolving Intelligent Systems
In this paper, some interesting characteristics of evolving intelligent systems are described. They are known as: the definition of the evolving intelligent systems, the applications, evolving pattern classification, evolving control, evolving identification, evolving prediction, and evolving optimization. For the details of the described methods, please see the references. Evolving systems, id...
متن کاملPotentials of Evolving Linear Models in Tracking Control Design for Nonlinear Variable Structure Systems
Evolving models have found applications in many real world systems. In this paper, potentials of the Evolving Linear Models (ELMs) in tracking control design for nonlinear variable structure systems are introduced. At first, an ELM is introduced as a dynamic single input, single output (SISO) linear model whose parameters as well as dynamic orders of input and output signals can change through ...
متن کاملReal time robust speech detection for text independent speaker recognition
Speaker recognition systems employ a speech detection algorithm and use only frames detected as speech for further processing. The accuracy obtained by a speaker recognition system depends on the method that is used to detect speech, in particular for real-life deployments where the incoming speech varies significantly in loudness and noise characteristics. Also, actual deployments mandate real...
متن کاملAn Intelligent System’s Approach for Revitalization of Brown Fields using only Production Rate Data
State-of-the-art data analysis in production allows engineers to characterize reservoirs using production data. This saves companies large sums that should otherwise be spend on well testing and reservoir simulation and modeling. There are two shortcomings with today’s production data analysis: It needs bottom-hole or well-head pressure data in addition to data for rating reservoirs’ characteri...
متن کامل