Diagnostic instrumental speech quality assessment in a super-wideband context

Nicolas Côté 1, * Vincent Koehl 1 Sebastian Möller 2 Alexander Raake 2 Marcel Wältermann 2 Valérie Gautier-Turbin 3
* Corresponding author
1 Lab-STICC_UBO_CID_IHSEV
IBNM - Institut Brestois du Numérique et des Mathématiques, Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : Speech quality models usually estimate the integral quality of the degraded speech files. Such quality values do not inform system developers and telephone service providers on the perceived degradation introduced by the system under study. This paper describes a new intrusive speech quality model, called Diagnostic Instrumental Assessment of Listening quality (DIAL), providing diagnostic information in both narrow-band and super-wideband contexts. Contrary to previous methods, this model estimates scores on four perceptual quality dimensions, Directness/Frequency content, Continuity, Noisiness and Loudness. These four dimensions are assumed to define the whole speech quality space.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.univ-brest.fr/hal-00638340
Contributor : Vincent Koehl <>
Submitted on : Wednesday, February 13, 2019 - 12:02:07 PM
Last modification on : Thursday, October 17, 2019 - 12:36:57 PM
Long-term archiving on : Tuesday, May 14, 2019 - 4:20:28 PM

File

12 (1).pdf
Publisher files allowed on an open archive

Identifiers

Citation

Nicolas Côté, Vincent Koehl, Sebastian Möller, Alexander Raake, Marcel Wältermann, et al.. Diagnostic instrumental speech quality assessment in a super-wideband context. PQS 2010, 3rd International Workshop on Perceptual Quality of Systems, International Speech Communication Association, Sep 2010, Bautzen, Germany. pp.65-70, ⟨10.21437/PQS.2010-12⟩. ⟨hal-00638340v2⟩

Share

Metrics

Record views

200

Files downloads

171