A Unified Theoretical Bayesian Model of Speech Communication

نویسندگان

  • Clément Moulin-Frier
  • Jean-Luc Schwartz
  • Julien Diard
  • Pierre Bessière
چکیده



 Based on a review of models and theories in speech communication, this paper proposes an original Bayesian framework able to express each of them in a unified way. This framework allows to selectively incorporate motor processes in perception or auditory representations in production, thus implementing components of a perceptuo-motor link in speech communication processes. This provides a basis for future computational works on the joint study of perception, production and their coupling in speech communication. Keywords: Speech Communication, Cognitive Bayesian Modeling, Sensory-Motor interaction INTRODUCTION:
MODELS
AND
THEORIES
IN
SPEECH
 COMMUNICATION
 Speech communication involves a set of actuators for producing speech stimuli (enabling to control the orofacial system: lungs, glottis, jaw, tongue, lips, velum) and a set of sensors for perceiving them (audition of course, but also vision for lipreading, and haptics and proprioception for sensing the state of the vocal tract). This enables the speaker to control the task in speech production that is achieving the correct gestures for uttering the adequate sounds. Hence, speech production can be conceived as a typical robotics problem, involving proximal control in reference to given distal objectives, together with learning, adaptability, or any other problem

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Improved Bayesian Training for Context-Dependent Modeling in Continuous Persian Speech Recognition

Context-dependent modeling is a widely used technique for better phone modeling in continuous speech recognition. While different types of context-dependent models have been used, triphones have been known as the most effective ones. In this paper, a Maximum a Posteriori (MAP) estimation approach has been used to estimate the parameters of the untied triphone model set used in data-driven clust...

متن کامل

A UNIFIED MODEL FOR RESOURCE-CONSTRAINED PROJECT SCHEDULING PROBLEM WITH UNCERTAIN ACTIVITY DURATIONS

In this paper we present a unified (probabilistic/possibilistic) model for resource-constrained project scheduling problem (RCPSP) with uncertain activity durations and a concept of a heuristic approach connected to the theoretical model. It is shown that the uncertainty management can be built into any heuristic algorithm developed to solve RCPSP with deterministic activity durations. The esse...

متن کامل

Robust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks

Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...

متن کامل

Speech Enhancement Using Gaussian Mixture Models, Explicit Bayesian Estimation and Wiener Filtering

Gaussian Mixture Models (GMMs) of power spectral densities of speech and noise are used with explicit Bayesian estimations in Wiener filtering of noisy speech. No assumption is made on the nature or stationarity of the noise. No voice activity detection (VAD) or any other means is employed to estimate the input SNR. The GMM mean vectors are used to form sets of over-determined system of equatio...

متن کامل

Simultaneous recognition of words and prosody in the Boston University Radio Speech Corpus

This paper describes automatic speech recognition systems that satisfy two technological objectives. First, we seek to improve the automatic labeling of prosody, in order to aid future research in automatic speech understanding. Second, we seek to apply statistical speech recognition models of prosody for the purpose of reducing the word error rate of an automatic speech recognizer. The systems...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017