Collection and annotation of Malay conversational speech corpus

Abstract This paper presents a corpus-based perspective on the phonetic fusion of disyllabic words in a Chinese conversational speech corpus. Four categorical types that reflect the phonological features of reduction degrees are automatically derived from gradient, acoustic properties. A transcription experiment is conducted with the most common disyllabic words. Both automatic derivation by acoustic signals and human transcription by perceptual judgment refer to the same sound inventory. We have shown that the complete form of fusion occurring in conversation need not be legitimate syllables and it appears consistently in the form of syllable merger that represents a group of phonetic variants.

Download Full-text

Creating a Spontaneous Conversational Speech Corpus

Data Science Journal ◽

10.2481/dsj.10-011 ◽

2012 ◽

Vol 10 ◽

pp. 42-51 ◽

Cited By ~ 1

Author(s):

Maria Husin ◽

Darryl Stewart ◽

Ji Ming ◽

F J Smith

Keyword(s):

Conversational Speech ◽

Speech Corpus

Download Full-text

The Montclair Map Task: Balance, Efficacy, and Efficiency in Conversational Interaction

Language and Speech ◽

10.1177/0023830918775435 ◽

2018 ◽

Vol 62 (2) ◽

pp. 378-398 ◽

Cited By ~ 3

Author(s):

Jennifer S Pardo ◽

Adelya Urmanche ◽

Hannah Gash ◽

Jaclyn Wiener ◽

Nicholas Mason ◽

...

Keyword(s):

Task Performance ◽

Matching Task ◽

Data Repository ◽

Map Matching ◽

State University ◽

Conversational Speech ◽

Same Sex ◽

Speech Corpus ◽

Conversational Interaction ◽

Task Oriented

This paper introduces a conversational speech corpus collected during the completion of a map-matching task that is available for research purposes via the Montclair State University Digital Commons Data Repository. The Montclair Map Task is a new, role-neutral conversational task that involves paired iconic maps with labeled landmarks and a path drawn from a start point, around various landmarks, to a finish mark. One advantage of this task-oriented corpus is the ability to derive independent objective measures of task performance for both members of a conversational pair that can be related to aspects of communicative style. A total of 96 native English speakers completed the task in 16 same-sex female, 16 same-sex male, and 16 mixed-sex pairings. Conversations averaged 32 minutes in duration, yielding approximately 217,000 words. The transcription protocol delineates events such as speaking turns, inter-turn intervals, landmark phrases, fillers, pauses, overlaps, and backchannels, making this corpus a useful tool for investigating dynamics of conversational interaction. Analyses of communication efficacy and efficiency reveal that male pairs of talkers were less efficient than female and mixed-sex pairs with respect to partner map-matching task performance.

Download Full-text

Reliability of Clinician Judgments of Severity of Phonological Impairment

American Journal of Speech-Language Pathology ◽

10.1044/1058-0360.0403.39 ◽

1995 ◽

Vol 4 (3) ◽

pp. 39-46 ◽

Cited By ~ 7

Author(s):

Susan K. Rafaat ◽

Susan Rvachew ◽

Rebecca S. C. Russell

Keyword(s):

Conversational Speech ◽

Speech Language Pathologists ◽

Age Appropriate ◽

Citation Form ◽

Phonological Abilities ◽

Preschool Aged Children

Pairs of speech-language pathologists independently rated severity of phonological impairment for 45 preschoolers, aged 30 to 65 months. Children were rated along a continuum from normal to profound. In addition to judging overall severity of impairment, the clinicians provided separate ratings based on citation form and conversational samples. A judgment of intelligibility of conversational speech was also required. Results indicated that interclinician reliability was adequate (80% agreement) for older preschool-aged children (4-1/2 years and above) but that judgments by speechlanguage pathologists were not sufficiently reliable for children under 3-1/2 years of age 40% agreement). Children judged to have age appropriate phonological abilities were not clearly distinguishable from children judged to have a mild delay. Educating speech-language pathologists regarding the normative phonological data that are available with respect to young preschoolers, and ensuring that such data are readily accessible for assessment purposes, is required.

Download Full-text