| 1 |
A Study of Data Augmentation for ASR Robustness in Low Bit Rate Contact Center Recordings Including Packet Losses
|
|
|
|
In: Applied Sciences; Volume 12; Issue 3; Pages: 1580 (2022)
|
|
Abstract:
Client conversations in contact centers are nowadays routinely recorded for a number of reasons—in many cases, just because it is required by current legislation. However, even if not required, conversations between customers and agents can be a valuable source of information about clients or future clients, call center agents, markets trends, etc. Analyzing these recordings provides an excellent opportunity to be aware about the business and its possibilities. The current state of the art in Automatic Speech Recognition (ASR) allows this information to be effectively extracted and used. However, conversations are usually stored in highly compressed ways to save space and typically contain packet losses that produce short interruptions in the speech signal due to the common use of Voice-over-IP (VoIP) in these systems. These effects, and especially the last one, have a negative impact on ASR performance. This article presents an extensive study on the importance of these effects on modern ASR systems and the effectiveness of using several techniques of data augmentation to increase their robustness. In addition, ITU-T G.711, a well-known Packet Loss Concealment (PLC) method is applied in combination with data augmentation techniques to analyze ASR performance improvement on signals affected by packet losses.
|
|
Keyword:
data augmentation; Fisher Spanish; G.711; packet loss concealment; packet losses; speech recognition
|
|
URL: https://doi.org/10.3390/app12031580
|
|
BASE
|
|
Hide details
|
|
|
| 2 |
Evaluating Video Conferencing Software for Remote Working Using Two-Stage Grey MCDM: A Case Study from Vietnam
|
|
|
|
In: Mathematics; Volume 10; Issue 6; Pages: 946 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Reversal of G-Quadruplexes’ Role in Translation Control When Present in the Context of an IRES
|
|
|
|
In: Biomolecules; Volume 12; Issue 2; Pages: 314 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Sampling of the Spanish campus novel ; Muestreo de la novela de campus española
|
|
|
|
In: Monteagudo. Revista de Literatura Española, Hispanoamericana y Teoría de la Literatura; No. 27 (2022): “El traje que vestí mañana”. One hundred years of Trilce (1922-2022); 179-200 ; Monteagudo. Revista de Literatura Española, Hispanoamericana y Teoría de la Literatura; Núm. 27 (2022): "El traje que vestí mañana". Cien años de Trilce (1922-2022).; 179-200 ; 1989-6166 ; 0580-6712 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Making the city through participatory video: implications for urban geography
|
|
|
|
BASE
|
|
Show details
|
|
|
| 7 |
Qu'est-ce qu'une (bonne) explication pragmatique de la fiction ?
|
|
|
|
In: Séminaire sur la fiction ; https://hal.archives-ouvertes.fr/hal-03479487 ; Séminaire sur la fiction, Jocelyn BENOIST, Oct 2021, Paris, France (2021)
|
|
BASE
|
|
Show details
|
|
|
| 8 |
«MY CHILDREN» BY G. YAKHINA AS A HISTORICAL NOVEL THROUGH THE PRISM OF THE LEXICAL AND SEMANTIC FIELD «GERMAN» ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Acquiring normative data with the German ICS-G digital in children (3;0-5;11 yrs.) with and without Speech-Sound Disorders (SSD) ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
The Cap-Binding Complex CBC and the Eukaryotic Translation Factor eIF4E: Co-Conspirators in Cap-Dependent RNA Maturation and Translation
|
|
|
|
In: Cancers; Volume 13; Issue 24; Pages: 6185 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
E-Learning Platform Assessment and Selection Using Two-Stage Multi-Criteria Decision-Making Approach with Grey Theory: A Case Study in Vietnam
|
|
|
|
In: Mathematics; Volume 9; Issue 23; Pages: 3136 (2021)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Population geography I : epistemological opportunities of mixed methods
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Assessing post-disaster recovery using sentiment analysis (SA). The cases of L'Aquila (Italy), Chile and Haiti
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
La phonotaxe du russe dans la typologie des langues : focus sur la palatalisation
|
|
|
|
In: Actes de la 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole ; JEP-TALN-RECITAL 2020 - 6e conférence conjointe 33e Journées d'Études sur la Parole, 27e Traitement Automatique des Langues Naturelles, 22e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues ; https://hal.archives-ouvertes.fr/hal-02798512 ; JEP-TALN-RECITAL 2020 - 6e conférence conjointe 33e Journées d'Études sur la Parole, 27e Traitement Automatique des Langues Naturelles, 22e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues, Jun 2020, Nancy, France. pp.36-44 ; https://jep-taln2020.loria.fr/ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Fast multivariate empirical cumulative distribution function with connection to kernel density estimation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 16 |
The role of the social movements in social ennovation (SI): Euskaraldia, as a digital panopticon / Gizarte mugimenduen rola gizarte berrikuntzan: Euskaraldia, panoptiko digital gisa
|
|
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Settled rather than saddled Scythians: the easternmost Sakas
|
|
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Between Hind and Hellas: the Bactrian Bridgehead (with an Appendix on Indo-Hellenic interactions)
|
|
|
|
BASE
|
|
Show details
|
|
|
| 19 |
G. S. Rayshev: Communication Functions of the Modern Artist
|
|
|
|
BASE
|
|
Show details
|
|
|
| 20 |
Scoring Model in Operational Research on Cultural-Tourism: A Case Study in Kota Kinabalu, Sabah
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
