An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

Consider a discrete source producing a sequence of message letters from a finite alphabet. A single-letter distortion measure is given by a non-negative matrix (d ij ). The entryd ij measures the ?cost? or ?distortion? if letteriis reproduced at the receiver as letterj. The average distortion of a communications system (source-coder-noisy channel-decoder) is taken to bed= ? i.j P ij d ij whereP ij is the probability ofibeing reproduced asj. It is shown that there is a functionR(d) that measures the ?equivalent rate? of the source for a given level of distortion. For coding purposes where a leveldof distortion can be tolerated, the source acts like one with information rateR(d). Methods are given for calculatingR(d), and various properties discussed. Finally, generalizations to ergodic sources, to continuous sources, and to distortion measures involving blocks of letters are developed. In this paper a study is made of the problem of coding a discrete source of information, given afidelity criterionor ameasure of the distortionof the final recovered message at the receiving point relative to the actual transmitted message. In a particular case there might be a certain tolerable level of distortion as determined by this measure. It is desired to so encode the information that the maximum possible signaling rate is obtained without exceeding the tolerable distortion level. This work is an expansion and detailed elaboration of ideas presented earlier [1], with particular reference to the discrete case. We shall show that for a wide class of distortion measures and discrete sources of information there exists a functionR(d) (depending on the particular distortion measure and source) which measures, in a sense, the equivalent rateRof the source (in bits per letter produced) whendis the allowed distortion level. Methods will be given for evaluatingR(d) explicitly in certain simple cases and for evaluatingR(d) by a limiting process in more complex cases. The basic results are roughly that it is impossible to signal at a rate faster thanC/R(d) (source letters per second) over a memoryless channel of capacityC(bits per second) with a distortion measure less than or equal tod. On the other hand, by sufficiently long block codes it is possible to approach as closely as desired the rateC/R(d) with distortion leveld. Finally, some particular examples, using error probability per letter of message and other simple distortion measures, are worked out in detail.

Coding Theorems for a Discrete Source With a Fidelity CriterionInstitute of Radio Engineers, International Convention Record, vol. 7, 1959.

Principal characteristics of speech speech production models speech analysis and analysis-synthesis systems linear predictive coding (LPC) analysis speech coding speech synthesis speech recognition future directions of speech processing. Appendices: convolution and z-transform vector quantization algorithm neural nests.

Digital speech processing, synthesis, and recognition

A data network telephony system (99) includes a router (410) connected to a DNT-capable data network (500) and a wireless transceiver (400) and adapted to operate the transceiver (400) by a two-way narrow-band, multiple-channel, real-time duplex radio protocol, and a plurality of portable computer-enhanced communicator units (100, 200, 300 and 600), including microphone and speaker apparatus (105 and 106), each adapted to communicate with the router (410) by the two-way real-time duplex radio protocol and to process DNT calls.

Noise reduction techniques and apparatus for enhancing wireless data network telephony

This is the nal report of the rst year of the Artwork project. It contains a chapter devoted to each of the major three phases of the project. Chapter 1 contains the nal report on Phase One of the rst year of the Artwork project. The initial phase of the Artwork feasibility study was to perform a comparative analysis of language usage in spoken dialog, the modality of speech-to-speech translation, and in written text, the modality assumed for the development of most current MT systems including the CRL's. The objective was to establish a range of structural, functional and interpersonal characteristics for each modality which can be taken as processing requirements, to see which are associated with both modalities and which are associated with just one of the modalities, and, nally, to identify the relative importance of the diierent characteristics to successfully processing utterances produced under each modality. The tasks involved in carrying out the comparative analysis included: (1) the collection and transcription of the spoken data for the analysis (approximately an hour of taped interviews) and the preparation of the written data (EFE newswire articles), (2) the quantitative analysis of the transcriptions and texts with respect to a number of relevant linguistic characteristics, and (3) the comparison of the resultant analyses for diierences between dialogs and text. In addition, approximately midway through the project it was decided that (4) the impact of protocol on dialog was to be analyzed. Chapter 4 contains the results of tasks 1, 2, 3. Chapter 3, which contains the results of Phase Three of the project, contains the results of task 4. Chapter 2 contains the nal report on Phase Two of the project. The goal of this phase was to identify a number of translation problems that appear to be peculiar to dialog translation as opposed to text translation and to survey current MT system capabilities for dealing with these problems. The chapter is therefore divided into two part: a survey of dialog translation problems and a survey of current MT system techniques for dealing with them. Chapter 3 contains the nal report on Phase Three of the project. According to a revised plan of research, which was agreed to during the fth bimonthly reporting period, Phase Three of the project consists of (1) a study comparing dialogs collected within a push-to-talk protocol with dialogs collected within a cross-talk protocol and (2) identifying …

A summary statement.

Evaluation of voice pathology based on the estimation of vocal fold biomechanical parameters.

The impact of voice pathologies caused by physiological alterations of the vocal cords is becoming a very important issue due to vocal abuse and unhealthy habits. Early detection of incipient damage to the cords may help in improving the prognosis, treatment and care of these pathologies. Information derived from the speech signal may help in detecting early stages of pathology, and to prevent them by assisting experts in voice therapy to correct vocal abuse in children and in professionals depending on voice as, for example, speakers, singers or lecturers. The present paper is devoted to detecting the presence of certain pathologies in the voice or speech signal from the cepstral contents of the mucosal wave reconstructed by inverse filtering, using conclusions derived from the behavior of a 2-mass vocal cord model. This can be of application in speech and singing education, and in pathology screening.

Evidence of vocal cord pathology from the mucosal wave cepstral contents

Characterization of Parkinson’s disease dysarthria in terms of speech articulation kinematics

Pathology detection methods in vocal cords using the voice may benefit from the detection of the time and frequency patterns of the mucosal wave correlate. A description of the vocal folds is given in terms of the most relevant features related to vocal fold pathology in reference to the body-cover models of 2- and k-masses. A description of the mucosal wave correlate as the residual small-amplitude vibration when removing the body influence in the glottal aperture is given. The main features of the mucosal wave correlate are examined. Finally, a parameterization method based on this study and its possible applications to speech pathology detection are discussed.

Evidence of glottal source spectral features found in vocal fold dynamics

BioMet®Phon is a software application developed for the characterization of voice in voice quality evaluation Initially it was conceived as plain research code to estimate the glottal source from voice and obtain the biomechanical parameters of the vocal folds from the spectral density of the estimate This code grew to what is now the Glottex®Engine package (G®E) Further demands from users in laryngology and speech therapy fields instantiated the development of a specific Graphic User Interface (GUI’s) to encapsulate user interaction with the G®E This gave place to BioMet®Phon, an application which extracts the glottal source from voice and offers a complete parameterization of this signal, including distortion, cepstral, spectral, biomechanical, time domain, contact and tremor parameters The semantic capabilities of biomechanical parameters are discussed Study cases from its application to the field of laryngology and speech therapy are given and discussed Validation results in voice pathology detection are also presented Applications to laryngology, speech therapy, and monitoring neurological deterioration in the elder are proposed

/pdf/biomet-phon-a-system-to-monitor-phonation-quality-in-the-3wktjruyoh.pdf

Victoria Rodellar

Papers

Evaluation of voice pathology based on the estimation of vocal fold biomechanical parameters.

Evidence of vocal cord pathology from the mucosal wave cepstral contents

Characterization of Parkinson’s disease dysarthria in terms of speech articulation kinematics

Evidence of glottal source spectral features found in vocal fold dynamics

BioMet®Phon: A system to monitor phonation quality in the clinics