Testing and characterization of AI model in STT and TTS for phone applications

This work presents the design of a testbed to evaluate STT and TTS AI models in the context of phone applications, focusing on the Italian language and phone-quality audio. The system supports automated evaluation under configurable network impairments using a virtual audio pipeline on GNU/Linux

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2025-04-01
DOI
https://doi.org/10.5281/zenodo.15127616
Primary Topic
Speech Recognition and Synthesis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Testing and characterization of AI model in STT and TTS for phone applications

Zenodo (CERN European Organization for Nuclear Research)
Speech Recognition and Synthesis
article

Testing and characterization of AI model in STT and TTS for phone applications

article en

Abstract

This work presents the design of a testbed to evaluate STT and TTS AI models in the context of phone applications, focusing on the Italian language and phone-quality audio. The system supports automated evaluation under configurable network impairments using a virtual audio pipeline on GNU/Linux

Zenodo (CERN European Organization for Nuclear Research)
Kallyope (United States) (US)
Openalex Percentile: Top 74%
Speech Recognition and Synthesis
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.