A Large Speech Database for Brazilian Portuguese Spoken Language Research

2003 ◽  
pp. 193-196
Author(s):  
Carlos Alberto Ynoguti ◽  
Plínio Almeida Barbosa ◽  
Fábio Violaro
Keyword(s):  
Spoken Language ◽  
Brazilian Portuguese ◽  
Language Research ◽  
Speech Database

scholarly journals Indian Language Identification using Deep Learning

2020 ◽  
Vol 32 ◽  
pp. 01010
Author(s):  
Shubham Godbole ◽  
Vaishnavi Jadhav ◽  
Gajanan Birajdar
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Visual Representations ◽  
Spoken Language ◽  
Language Identification ◽  
Indian Language ◽  
Regular Method ◽  
Speech Database ◽  
Day By Day

Spoken language is the most regular method of correspondence in this day and age. Endeavours to create language recognizable proof frameworks for Indian dialects have been very restricted because of the issue of speaker accessibility and language readability. However, the necessity of SLID is expanding for common and safeguard applications day by day. Feature extraction is a basic and important procedure performed in LID. A sound example is changed over into a spectrogram visual portrayal which describes a range of frequencies in regard with time. Three such spectrogram visuals were generated namely Log Spectrogram, Gammatonegram and IIR-CQT Spectrogram for audio samples from the standardized IIIT-H Indic Speech Database. These visual representations depict language specific details and the nature of each language. These spectrograms images were then used as an input to the CNN. Classification accuracy of 98.86% was obtained using the proposed methodology.

The notation of signed texts

2001 ◽  
Vol 4 (1-2) ◽  
pp. 29-45 ◽  
Author(s):  
Elena Antinoro Pizzuto ◽  
Paola Pietrandrea
Keyword(s):  
General Problem ◽  
Spoken Language ◽  
Signed Languages ◽  
Signed Language ◽  
Language Research ◽  
Primary Means ◽  
Future Work

This paper focuses on some of the major methodological and theoretical problems raised by the fact that there are currently no appropriate notation tools for analyzing and describing signed language texts. We propose to approach these problems taking into account the fact that all signed languages are at present languages without a written tradition. We describe and discuss examples of the gloss-based notation that is currently most widely used in the analysis of signed texts. We briefly consider the somewhat paradoxical problem posed by the difficulty of applying the notation developed for individual signs to signs connected in texts, and the more general problem of clearly identifying and characterizing the constituent units of signed texts. We then compare the use of glosses in signed and spoken language research, and we examine the major pitfalls we see in the use of glosses as a primary means to explore and describe the structure of signed languages. On this basis, we try to specify as explicitly as possible what can or cannot be learned about the structure of signed languages using a gloss-based notation, and to provide some indications for future work that may aim to overcome the limitations of this notation.

The spoken language research laboratories (SLRL) at the University of Oregon

2020 ◽  
Vol 148 (4) ◽  
pp. 2746-2746
Author(s):  
Melissa M. Baese-Berk ◽  
Kaori Idemaru ◽  
Vsevolod Kapatsinski ◽  
Tyler Kendall ◽  
Charlotte Vaughn ◽  
...  
Keyword(s):  
Spoken Language ◽  
Language Research ◽  
The University

scholarly journals Designing and building SCoPE²: A spoken corpus of Brazilian Portuguese and L2-English

2020 ◽  
Vol 8 ◽  
pp. 49-64
Author(s):  
Giovani Santos
Keyword(s):  
University Students ◽  
Spoken Language ◽  
Theoretical Framework ◽  
Brazilian Portuguese ◽  
Lessons Learned ◽  
Corpus Pragmatics ◽  
Do It Yourself ◽  
Gathering Data ◽  
Selection Of

This paper presents the process of designing and building a bilingual spoken corpus in order to pragmatically analyse oral L2-English discourse produced by a group of Brazilian university students living in Ireland. It discusses some of the decisions made, challenges faced, and considerations taken while designing a do-it-yourself corpus with a theoretical framework grounded in Corpus Pragmatics. The main objective is to share the lessons learned by examining the steps of designing and building SCoPE², a bilingual spoken corpus, including the selection of participants, gathering data, and challenges in transcribing and coding spoken language with pragmatics in mind.

Sign in / Sign up

Export Citation Format

Share Document