2021
DOI: 10.1109/access.2021.3112535
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Speech Recognition: Systematic Literature Review

Abstract: A huge amount of research has been done in the field of speech signal processing in recent years. In particular, there has been increasing interest in the automatic speech recognition (ASR) technology field. ASR began with simple systems that responded to a limited number of sounds and has evolved into sophisticated systems that respond fluently to natural language. This systematic review of automatic speech recognition is provided to help other researchers with the most significant topics published in the las… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
17
0
3

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 60 publications
(34 citation statements)
references
References 91 publications
(129 reference statements)
0
17
0
3
Order By: Relevance
“…If participants are collecting language using at-home methods, there will likely be additional sources of noise (e.g., additional voices, background TV, movement) ( 131 ), which affects transcription accuracy and acoustic feature calculation. These methods will require participant training to minimize these effects, as well as various pre-processing software to filter out these interferences ( 132 – 134 ). In the absence of paid-for transcription services, researchers can also utilize Automatic-Speech-Recognition (ASR) to transcribe spoken language into text for easier data processing ( 135 ).…”
Section: State-of-the-art In Pain Methodsmentioning
confidence: 99%
“…If participants are collecting language using at-home methods, there will likely be additional sources of noise (e.g., additional voices, background TV, movement) ( 131 ), which affects transcription accuracy and acoustic feature calculation. These methods will require participant training to minimize these effects, as well as various pre-processing software to filter out these interferences ( 132 – 134 ). In the absence of paid-for transcription services, researchers can also utilize Automatic-Speech-Recognition (ASR) to transcribe spoken language into text for easier data processing ( 135 ).…”
Section: State-of-the-art In Pain Methodsmentioning
confidence: 99%
“…El vocabulario, la pronunciación y el dialecto son las principales técnicas en las que el PLN se enfoca, por lo que hace énfasis en la cantidad de palabras que deberían incluirse en el vocabulario, los problemas que pueden ocasionar una mala pronunciación de las palabras y el problema del reconocimiento del dialecto de distintas regiones donde manejan el idioma implementado. Por último, el uso del micrófono también es analizado, debido a que es un dispositivo que captura la voz y que incide radicalmente cuando se hacen entrenamientos y pruebas de datos con y sin su uso (Alharbi et al, 2021).…”
Section: Trabajos Relacionadosunclassified
“…El reconocimiento automático de voz es una de las aplicaciones en el área del PLN (Ankit et al, 2016), que tiene como objetivo fundamental la transcripción del habla, que se basa en secuencias de palabras representadas a través de ondas de los audios. (Alharbi et al, 2021) Una conversación comúnmente puede darse entre actores humanos y agentes artificiales, donde la naturaleza del discurso, el tamaño del vocabulario y el ancho de banda son aspectos relevantes y primordiales al momento de entrenar un sistema de Reconocimiento Automático de Voz (RAV) (Alharbi et al, 2021). Además, el RAV considera aspectos del lenguaje natural como semántica, sintaxis, gramática y la fonética, dada la variedad de sonidos del habla que pueden producir los seres humanos, que incluyen el ritmo, el acento, la pronunciación dialéctica, las entonaciones peculiares de una palabra para dar un significado u otro, e incluso las distintas malas pronunciaciones en ciertos fonemas como por ejemplo el rotacismo (Aguiar de Lima y Da Costa-Abreu, 2020).…”
unclassified
“…Speech is the major communication technique between people, it is necessary to comprehend, learn to read or write. Speech technology now enables robots to react quickly and correctly by using the voices of people instead of keyboards [2], [4].…”
Section: Introductionmentioning
confidence: 99%