Judith Markowitz

• Ph.D in linguistics
• CEO at J. Markowitz, Consultants

Speech-enabled, social robots are being designed to provide a range of services to humans but humans are not passive recipients of this technology. We have preconceptions and expectations about robots as well as deeply-ingrained emotional responses to the concept of robots sharing our world. We examine three roles that humans expect robots to play:...

Robots That Talk and Listen provides a forward-looking examination of speech and language in robots from technical, functional, and social perspectives. Contributors address cultural foundations as well as the linguistic skills and technologies that robots need to function effectively in real-world settings. Among the most difficult and complex is...

This book provides multiple perspectives regarding speech-enabled robots. Those perspectives include * hardware and software design * guidelines for implementing speech and language * the impact of culture and art on popular perceptions of robots * multimodal learning and teaching * visions of a robotic future.

This book provides a comprehensive vision of how humans can interact with speech-enabled social robots. It covers hardware, software, social and cultural aspects of research on human-computer interaction

SIRI has prompted new excitement about spoken language interfaces. Unfortunately, SIRI-inspired discussions make it easy to overlook the diversity of mobile markets in which speech recognition plays a critical role. This chapter examines three of those markets: factory/warehouse operations, offender mon­itoring, and robotics. Reflecting on some of...

This fourteen-chapter anthology *analyze the role of natural-language technology in the marketplace *advanced NLP methods and applications *innovative tools for physicians, educators, and translators

One characteristic that distinguishes speaker recognition (identification, verification, classification, tracking, etc.) from other biometrics is that it is designed to operate with devices and over channels that were created for other technologies and functions. That characteristic supports broad, inexpensive, and speedy deployments. The explosion...

This is a position paper on the following topic listed in the c all for contributions: Can audio formats be normalized for interoperability and conformance testing? How to deter mine that normalization? The position regarding the first question is that audio formats can be normalized. The response to the second question is a proposal that supports...

Speaker classification is a fundamental component of speaker identification and verification (SIV) technologies. This paper provides and overview of the many guises that classification takes within SIV systems.

The documents of a university were analyzed for the presence of sex-linked and sex-neutral language as a measure of the impact of regulation on language change. Documents from 1969-1972, the period just prior to the bulk of the sexist-language controversy, were compared with matching documents from 1978-1979; and documents covered by sexist-languag...

Since September 11, 2001 there has been a sharp increase in the use of biometric-based security, including speaker authentication. Some of the guidelines for developing usable speaker authentication dialogs correspond to basic principles that apply to the design of good speech recognition interactions. Developing effective speaker authentication di...

This paper argues that it is impossible to separate lexical and encyclopedic knowledge and describes an attempt to build a large lexical database that contains the range of information needed to make a parser or a text generation system interpret and use words and phrases correctly.

Speaker recognition refers to a collection of biometric technologies that use features of a person's voice to perform a range of operations, including authentication, identification, classification, differentiation and lie detection. Of those operations, speaker authentication - use of a person's voice to certify they are who they claim to be - is...

Information retrieval systems that support searching of large textual databases are typically accessed by trained search intermediaries who provide assistance to end users in bridging the gap between the languages of authors and inquirers. We are building a thesaurus in the form of a large semantic network io support interactive query expansion and...

Voice-biometrics refers to the technology or process of speech processing where voice can be used to verify a personal identity, unobtrusively and invisibly. This technology forms the subject of discussion in the article. Voice-biometrics systems can be categorized as belonging in two industries, speech processing and biometric security. Like other...

Speaker verification is a highly commercialized form of a group of technologies known as speaker recognition or voice biometrics. Voice biometric technologies include speaker identification, voice stress analysis and lie detection. The popularity of speech recognition is still a strong market driver for speaker verification.

Speaker recognition uses features of a person's voice to identify or verify that person. It is a well-established biometric with commercial systems that are more than 10 years old and deployed non-commercial systems that are more than 20 years old. This paper describes how speaker recognition systems work and how they are used in applications.

Speech-recognition systems depend almost exclusively on acoustic data, yet they are expected to perform as accurately as humans. Several features influence the accuracy and speed of a speech-recognition system: the recognition algorithms used, the size and nature of the vocabulary, the grammar, whether speech is continuous or discrete, and the spea...

This paper extends the approach to feature structures developed in Johnson (1991a), which uses Schönfinkel-Bernays' formulae to express feature structure constraints. These are shown to be a disjunctive generalization of Datalog clauses, as used ...

Semantic networks need many more links than traditional ones include if they are to function as adequate models of human memory. Many tasks benefit from cognitively realistic representations. Such cognitively realistic models of human reasoning processes require a deep understanding of the logical properties of their links. This paper argues for th...

This paper argues that it is impossible to separate lexical and encyclopedic knowledge and describes an attempt to build a large lexical database that contains the range of information needed to make a parser or a text generation system interpret and use words and phrases correctly.

Word definition tasks are regarded as one of the most accurate measures of intelligence, yet little of the research on the development of defining style has been used to develop those tasks. This paper examines the research on defining, showing the wealth of information about cognitive and linguistic development which can be gleaned from studying c...

Information retrieval systems that support searching of large textual databases are typically accessed by trained search intermediaries who provide assistance to end users in bridging the gap between the languages of authors and inquirers. We are building a thesaurus in the form of a large semantic network to support interactive query expansion and...

Natural language processing systems need large lexicons containing explicit information about lexical-semantic relationships, selection restrictions, and verb categories. Because the labor involved in constructing such lexicons by hand is overwhelming, we have been trying to construct lexical entries automatically from information available in the...