Monitoring self-produced speech variability in native and learned languages

Purpose Current approaches to assessing sentence-level speech variability rely on measures that quantify variability across utterances and use normalization procedures that alter raw trajectory data. The current work tests the feasibility of a less restrictive nonlinear approach—recurrence quantification analysis (RQA)—via a procedural example and subsequent analysis of kinematic data. Method To test the feasibility of RQA, lip aperture (i.e., the Euclidean distance between lip-tracking sensors) was recorded for 21 typically developing adult speakers during production of a simple utterance. The utterance was produced in isolation and in carrier structures differing just in length or in length and complexity. Four RQA indices were calculated: percent recurrence (%REC), percent determinism (%DET), stability (MAXLINE), and stationarity (TREND). Results Percent determinism (%DET) decreased only for the most linguistically complex sentence; MAXLINE decreased as a function of linguistic complexity but increased for the longer-only sentence; TREND decreased as a function of both length and linguistic complexity. Conclusions This research note demonstrates the feasibility of using RQA as a tool to compare speech variability across speakers and groups. RQA offers promise as a technique to assess effects of potential stressors (e.g., linguistic or cognitive factors) on the speech production system.

Download Full-text

Speech Assistance for Persons With Speech Impediments Using Artificial Neural Networks

Volume 3: Biomedical and Biotechnology Engineering ◽

10.1115/imece2017-71027 ◽

2017 ◽

Author(s):

Ramy Mounir ◽

Redwan Alqasemi ◽

Rajiv Dubey

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Deep Learning ◽

Speech Recognition ◽

Automatic Speech Recognition ◽

Challenging Problem ◽

Speech Impairment ◽

Recognition Model ◽

Wide Range ◽

Speech Variability

This work focuses on the research related to enabling individuals with speech impairment to use speech-to-text software to recognize and dictate their speech. Automatic Speech Recognition (ASR) tends to be a challenging problem for researchers because of the wide range of speech variability. Some of the variabilities include different accents, pronunciations, speeds, volumes, etc. It is very difficult to train an end-to-end speech recognition model on data with speech impediment due to the lack of large enough datasets, and the difficulty of generalizing a speech disorder pattern on all users with speech impediments. This work highlights the different techniques used in deep learning to achieve ASR and how it can be modified to recognize and dictate speech from individuals with speech impediments.

Download Full-text

Age-related differences in speech variability among women

Journal of Communication Disorders ◽

10.1016/0021-9924(94)90010-8 ◽

1994 ◽

Vol 27 (1) ◽

pp. 49-64 ◽

Cited By ~ 38

Author(s):

Richard J. Morris ◽

W.S. Brown

Keyword(s):

Age Related ◽

Speech Variability

Download Full-text

Learning Speech Variability in Discriminative Acoustic Model Adaptation

IEICE Transactions on Information and Systems ◽

10.1587/transinf.e93.d.2370 ◽

2010 ◽

Vol E93-D (9) ◽

pp. 2370-2378

Author(s):

Shoei SATO ◽

Takahiro OKU ◽

Shinichi HOMMA ◽

Akio KOBAYASHI ◽

Toru IMAI

Keyword(s):

Acoustic Model ◽

Model Adaptation ◽

Speech Variability

Download Full-text

LOSING THE FLAVOUR? FROM ORATURE TO LITERATURE, AND ON CHOICES WHEN COMPILING DICTIONARIES FOR UN WRITTEN AFRICAN LANGUAGES

Southern African Journal for Folklore Studies ◽

10.25159/1016-8427/708 ◽

2016 ◽

Vol 25 (3) ◽

Author(s):

E Wolff

Keyword(s):

Oral Communication ◽

Natural Process ◽

African Languages ◽

Bilingual Dictionary ◽

Western Scholarship ◽

Speech Variability ◽

The Impact

Any hitherto unwritten language, in Africa as elsewhere, as soon as it becomes the object of linguistic and philological documentation and research, automatically crosses the Rubicon from oral to written and undergoes the first steps from orature to literature. This almost natural process may be studied under at least two perspectives: that of the linguistic and cultural ‘costs” of such transition, and that of the ideological burden in terms of stereotype and prejudice when researchers with a ‘Western’ background (by extension including researchers, also in Africa, who have been trained under the impact of ‘Western’ scholarship) approach languages and cultures of ‘others’. This links up with lexicographic work on languages which are predominantly or exclusively used for oral communication, by influencing the choices that lexicographers face in terms of lemma identification and speech variability when compiling the – often first ever – bilingual dictionary of a hitherto unwritten language.

Download Full-text

Speech variability and prosody in childhood apraxia of speech

The Journal of the Acoustical Society of America ◽

10.1121/1.4934145 ◽

2015 ◽

Vol 138 (3) ◽

pp. 1944-1944

Author(s):

Toby Macrae ◽

Kaitlin Lansford ◽

Emily Berteau

Keyword(s):

Apraxia Of Speech ◽

Childhood Apraxia Of Speech ◽

Speech Variability

Download Full-text

Introducción del discurso directo en el latín tardío

Acta Antiqua Academiae Scientiarum Hungaricae ◽

10.1556/068.2019.59.1-4.43 ◽

2020 ◽

Vol 59 (1-4) ◽

pp. 489-503

Author(s):

Jana Mikulová

Keyword(s):

Direct Speech ◽

Patterns Of Use ◽

Speech Variability ◽

Basic Characteristics

Summary:This paper examines verbs of speech used for introducing direct speech in Late Latin and changes which occurred from Classical to Late Latin. It focuses on four verbal forms which were previously identified as the most frequent in selected Late Latin texts, namely inquit, ait, dicens, and dixit. Their properties and patterns of use are examined and their development into quotative markers are considered. It is shown that while in Classical Latin inquit prevails, in Late Latin the range of verbal forms is wider and includes verbal forms that in Classical texts almost never appeared or had different functions than introducing direct speech. It is argued that despite some signs of grammaticalization, none of the examined forms has become a fully developed quotative marker. Thus, concerning the means for introducing direct speech, variability and heterogeneity are the basic characteristics of Late Latin texts.

Download Full-text