scholarly journals Estimation of Speech Intelligibility Using Perceptual Speech Quality Scores

10.5772/16822 ◽  
2011 ◽  
Author(s):  
Kazuhiro Kondo
Keyword(s):  
Speech Intelligibility ◽  
Speech Quality

scholarly journals A Robust Dual-Microphone Generalized Sidelobe Canceller Using a Bone-Conduction Sensor for Speech Enhancement

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1878
Author(s):  
Yi Zhou ◽  
Haiping Wang ◽  
Yijing Chu ◽  
Hongqing Liu
Keyword(s):  
Speech Enhancement ◽  
Speech Intelligibility ◽  
Bone Conduction ◽  
Speech Quality ◽  
Generalized Sidelobe Canceller ◽  
Spatially Distributed ◽  
Interference Signals ◽  
Adaptive Noise ◽  
Adaptive Noise Canceller ◽  
Sidelobe Canceller

The use of multiple spatially distributed microphones allows performing spatial filtering along with conventional temporal filtering, which can better reject the interference signals, leading to an overall improvement of the speech quality. In this paper, we propose a novel dual-microphone generalized sidelobe canceller (GSC) algorithm assisted by a bone-conduction (BC) sensor for speech enhancement, which is named BC-assisted GSC (BCA-GSC) algorithm. The BC sensor is relatively insensitive to the ambient noise compared to the conventional air-conduction (AC) microphone. Hence, BC speech can be analyzed to generate very accurate voice activity detection (VAD), even in a high noise environment. The proposed algorithm incorporates the VAD information obtained by the BC speech into the adaptive blocking matrix (ABM) and adaptive noise canceller (ANC) in GSC. By using VAD to control ABM and combining VAD with signal-to-interference ratio (SIR) to control ANC, the proposed method could suppress interferences and improve the overall performance of GSC significantly. It is verified by experiments that the proposed GSC system not only improves speech quality remarkably but also boosts speech intelligibility.

Quantifying the Relation Between Speech Quality and Speech Intelligibility

1995 ◽  
Vol 38 (3) ◽  
pp. 714-725 ◽  
Author(s):  
Jill E. Preminger ◽  
Dianne J. Van Tasell
Keyword(s):  
Speech Intelligibility ◽  
Normal Hearing ◽  
Speech Quality ◽  
Category Rating ◽  
Single Dimension ◽  
Quality Dimensions ◽  
Highly Correlated ◽  
Quality Measurements

The purpose of the present research was to examine the relation between speech quality and speech intelligibility. Speech quality measurements were made using continuous discourse and a category rating procedure for the following dimensions: intelligibility, pleasantness, loudness, effort, and total impression. Measurements were made using a group of listeners with normal hearing for a set of stimulus conditions in which intelligibility varied, and for a set of stimulus conditions in which intelligibility was held constant near 100%. When ratings were made for a set of stimulus conditions in which intelligibility was allowed to vary (a) intersubject reliability was high (i.e., different listeners interpreted the dimensions in a similar manner); and (b) the speech quality dimensions of intelligibility, effort, and loudness were indistinguishable. When ratings were made for a set of stimulus conditions in which intelligibility was held constant (a) intersubject reliability was reduced, indicating that different listeners interpreted the dimensions in different ways; (b) most listeners rated each dimension differently, indicating that the dimensions were unique; and (c) across listeners, no single dimension was highly correlated with total impression. These results can be used in order to examine the relation between speech quality and speech intelligibility.

Effect of Slow-Acting Wide Dynamic Range Compression on Measures of Intelligibility and Ratings of Speech Quality in Simulated-Loss Listeners

2005 ◽  
Vol 48 (3) ◽  
pp. 702-714 ◽  
Author(s):  
Peninah S. Rosengard ◽  
Karen L. Payton ◽  
Louis D. Braida
Keyword(s):  
Hearing Loss ◽  
Speech Intelligibility ◽  
Dynamic Range ◽  
Speech Quality ◽  
Subjective Ratings ◽  
Subjective Measures ◽  
Wide Dynamic Range ◽  
Dynamic Range Compression ◽  
Amplitude Compression ◽  
Moderate Hearing Loss

The purpose of this study was twofold: (a) to determine the extent to which 4-channel, slow-acting wide dynamic range amplitude compression (WDRC) can counteract the perceptual effects of reduced auditory dynamic range and (b) to examine the relation between objective measures of speech intelligibility and categorical ratings of speech quality for sentences processed with slow-acting WDRC. Multiband expansion was used to simulate the effects of elevated thresholds and loudness recruitment in normal hearing listeners. While some previous studies have shown that WDRC can improve both speech intelligibility and quality, others have found no benefit. The current experiment shows that moderate amounts of compression can provide a small but significant improvement in speech intelligibility, relative to linear amplification, for simulated-loss listeners with small dynamic ranges (i.e., flat, moderate hearing loss). This benefit was found for speech at conversational levels, both in quiet and in a background of babble. Simulated-loss listeners with large dynamic ranges (i.e., sloping, mild-to-moderate hearing loss) did not show any improvement. Comparison of speech intelligibility scores and subjective ratings of intelligibility showed that listeners with simulated hearing loss could accurately judge the overall intelligibility of speech. However, in all listeners, ratings of pleasantness decreased as the compression ratio increased. These findings suggest that subjective measures of speech quality should be used in conjunction with either objective or subjective measures of speech intelligibility to ensure that participant-selected hearing aid parameters optimize both comfort and intelligibility.

A Methodology for the Evaluation of Real-Time Speech Digitization

1983 ◽  
Vol 27 (1) ◽  
pp. 104-107 ◽  
Author(s):  
Thomas R. Edman ◽  
Stephen V. Metz
Keyword(s):  
Human Factors ◽  
Experimental Method ◽  
Real Time ◽  
Speech Intelligibility ◽  
Speech Quality ◽  
Design Issues ◽  
Commercial Speech ◽  
Store And Forward

Real-time speech digitizing technologies underlie such modern communications products as voice store and forward systems and digital PBX's. Among the human factors design issues associated with this technology, three of particular importance can be identified: i) speaker identifiability, ii) acceptability of speech quality, and iii) speech intelligibility. An experimental method for addressing issues of identifiability and intelligibility was developed and used to compare a commercial speech digitizing device with a standard toll quality telephone channel. It was found that the identifiability and acceptability of the telephone was slightly superior to the digitized speech. Additionally, results on an MRT showed intelligibility scores somewhat below optimal.

The Effects of Digital Quantization Error on Speech Intelligibility and Perceived Speech Quality

1991 ◽  
Vol 34 (1) ◽  
pp. 189-196 ◽  
Author(s):  
Richard W. Harris ◽  
Robert H. Brey ◽  
Yuan-Shu Chang ◽  
B. Diann Soria ◽  
Laurence M. Hilton
Keyword(s):  
Speech Intelligibility ◽  
Perceived Quality ◽  
Speech Quality ◽  
Quantization Error ◽  
Floating Point ◽  
Point Data

The effects of digital quantization error upon speech intelligibility and perceived speech quality, for normally hearing subjects, were investigated for digitized speech processed to simulate 6-, 8-, 10-, 12-, 14-, and 16-bit integer conversion and 2-, 3-, 4-, 5-, 6-, and 7-bit floating-point conversion. For the integer data, there were no significant differences in speech intelligibility for 8- to 16-bit conversion. Only 6-bit integer conversion at 55 dB SPL resulted in a significant degradation in speech intelligibility. For the floating-point data, there were no significant differences in speech intelligibility for 2- to 7-bit floating-point conversion. However, results of the perceived quality experiment appeared to be more sensitive to differences among the various conditions. Speech processed using 12-, 14-, and 16-bit integer conversion was judged to be superior to speech processed using the 6-, 8-, and 10-bit integer conditions. Speech processed using 5-, 6-, and 7-bit floating-point conversion was judged to be superior to speech processed using 2-, 3-, and 4-bit floating-point conversion.

scholarly journals SINTETINĖS ŠNEKOS KOKYBĖS VERTINIMAS: KELIŲ KOMPIUTERINIŲ SINTEZATORIŲ LYGINAMASIS TYRIMAS

Psichologija ◽  
2002 ◽  
Vol 25 ◽  
pp. 72-96 ◽  
Author(s):  
Albinas Bagdonas ◽  
Feliksas Laugalys
Keyword(s):  
Comparative Study ◽  
Speech Intelligibility ◽  
Speech Quality ◽  
Natural Speech ◽  
Synthetic Speech ◽  
Human Speech ◽  
Previous Version ◽  
Computer Based ◽  
Improve Correlation

Straipsnyje pateikiami kelių versijų lietuviškos ir rusiškos sintetinės šnekos suprantamumo ir lietuviškos, rusiškos, vengriškos bei itališkos sintetinių šnekų patrauklumo duomenys. Lietuvių ir rusų diktorių kalba yra suprantamesnė nei atitinkama sintetinė. Ankstesnė rusiškos šnekos sintezė blogesnė nei lietuviška ar patobulinta rusiška sintezė (PRS). Pagal sintetinamų garsų charakteristikas aiškėja dvi priešingos PRS tendencijos - pagal bendrą atpažinimo klaidų mažėjimą ji artėja prie natūralios šnekos, tačiau pagal klaidų homogeniškumą nuo pastarosios tolsta. Kadangi pirmoji tendencija vyrauja, bendra atstojamoji rodo PRS gerėjimą.PRS suprantamumo ir patrauklumo koreliacija taip pat rodo jos didesnį artumą natūraliai šnekai. Tiriamiesiems PRS yra patrauklesnė nei ankstesnė rusiškos sintezės versija. Pastaroji, tiriamųjų nuomone, panašesne į roboto šneką, o PRS - į blogą, tačiau jau žmogaus šnekos versiją.Pagal patrauklumo duomenis natūralią šneką labiausiai vertina vengrų klausytojai, o kritiškiausi jos atžvilgiu yra italai. Visos tirtos sintetinių šnekų versijos vertinamos kaip mažiau patrauklios nei natūrali šneka, tačiau jas patobulinus šis vertinimas švelnėja. EVALUATION OF SYNTHETIC SPEECH QUALITY: A COMPARATIVE STUDY OF SEVERAL COMPUTER-BASED SPEECH SYNTHESIZERS Albinas Bagdonas, Feliksas Laugalys SummaryThis paper examines some versions of Lithuanian and Russian synthetic speech intelligibility and Lithuanian, Russian, Hungarian and Italian synthetic speech acceptability. The speech of both Russian and Lithuanian speaker is more intelligible than Russian or Lithuanian synthesis. Previous version of Russian synthesis is worse than Lithuanian and improved Russian synthesis (IRS). Study of characteristics of IRS sounds shows two opposite tendencies - according to the general quantity of mistake reduction this version is tending towards the natural speech, but according to the homogeneity of mistakes, it moves away. As the first tendency is clearly dominant, the general resultant in the new version shows a tend to improve. Correlation between intelligibility and acceptability of IRS deals possibility of small progress towards the natural speech. The IRS is more acceptable to subjects than previous version. The old synthesis is viewed as a rather decent instance of a robot's speech, while the IRS - as a poor variant of human speech. Acceptability studies showed natural speech more enjoyed by Hungarian listeners and more critical by Italian. All versions of synthetic speech were judged as less acceptable than natural but after improvement most of listeners changed their mind.

Sign in / Sign up

Export Citation Format

Share Document