Mahdie Karbasi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mahdie Karbasi has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Dorothea Kolossa
Technische Universität Berlin
3 shared publications Ahmed Hussen Abdelaziz
2 shared publicationsDorothea Kolossa
Cognitive Signal Processing Group, Faculty of Electrical Engineering and Information Technology, Ruhr University Bochum, 44801, NRW, Germany
2 shared publicationsSteffen Zeiler
Cognitive signal processing group, Electrical engineering department, Ruhr-Universitt Bochum, Universittsstrae 150, Bochum, NRW, Germany
2 shared publicationsHendrik Meutzner
1 shared publicationJan Freiwald
Ruhr University Bochum
1 shared publication
Latest Publications
- 14 September 2022
- Published by Elsevier in Hearing Research
- Vol. 426, 108606
ASR-based speech intelligibility prediction: A review
- 14 September 2022
- Published by Elsevier in Hearing Research
- Vol. 426, 108606
ASR-based speech intelligibility prediction: A review
- 30 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 30 (23299290) , 2141-2155
Microscopic and Blind Prediction of Speech Intelligibility: Theory and Practice
Being able to estimate speech intelligibility without the need for listening tests would confer great benefits for a wide range of speech processing applications. Many attempts have therefore been made to introduce an objective, and ideally reference-free measure for this purpose. Most works analyze speech intelligibility prediction (SIP) methods from a macroscopic point of view, averaging over longer time spans. This paper, in contrast, presents a theoretical framework for the microscopic evaluation of SIP methods. Within our framework, a Statistically estimated Accuracy based on Theory (StAT) is derived, which numerically quantifies the statistical limitations inherent in microscopic SIP. A state-of-the-art approach to microscopic SIP, namely, the use of automatic speech recognition (ASR) to directly predict listening test results, is evaluated within this framework. The practical results are in good agreement with the theory. As the final contribution, a fully blind DIscriminative Speech intelligibility Predictor (DISP) is introduced and is also evaluated within the StAT framework. It is shown that this novel, blind estimator can predict intelligibility as well as—and often even with better accuracy than—the non-blind ASR-based approach, and that its results are again in good agreement with its theoretically derived performance potential.
- 30 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 30 (23299290) , 2141-2155
Microscopic and Blind Prediction of Speech Intelligibility: Theory and Practice
Being able to estimate speech intelligibility without the need for listening tests would confer great benefits for a wide range of speech processing applications. Many attempts have therefore been made to introduce an objective, and ideally reference-free measure for this purpose. Most works analyze speech intelligibility prediction (SIP) methods from a macroscopic point of view, averaging over longer time spans. This paper, in contrast, presents a theoretical framework for the microscopic evaluation of SIP methods. Within our framework, a Statistically estimated Accuracy based on Theory (StAT) is derived, which numerically quantifies the statistical limitations inherent in microscopic SIP. A state-of-the-art approach to microscopic SIP, namely, the use of automatic speech recognition (ASR) to directly predict listening test results, is evaluated within this framework. The practical results are in good agreement with the theory. As the final contribution, a fully blind DIscriminative Speech intelligibility Predictor (DISP) is introduced and is also evaluated within the StAT framework. It is shown that this novel, blind estimator can predict intelligibility as well as—and often even with better accuracy than—the non-blind ASR-based approach, and that its results are again in good agreement with its theoretically derived performance potential.
- 16 May 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 655-666
Toward Robust Mispronunciation Detection via Audio-Visual Speech Recognition
- 16 May 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 655-666
Toward Robust Mispronunciation Detection via Audio-Visual Speech Recognition
- 8 September 2016
- Published by International Speech Communication Association
Blind Non-Intrusive Speech Intelligibility Prediction Using Twin-HMMs
- 8 September 2016
- Published by International Speech Communication Association
Blind Non-Intrusive Speech Intelligibility Prediction Using Twin-HMMs
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 624-628
Twin-HMM-based non-intrusive speech intelligibility prediction
Most of the objective measures employed for speech intelligibility prediction require a clean reference signal, which is not accessible in all realistic scenarios. In this paper, we propose to re-synthesize the relevant features of the clean signal using only the noisy speech signal and utilize them inside an intelligibility prediction framework which requires a reference. A statistical model called twin hidden Markov model (THMM) is used to synthesize the clean speech features. For the intelligibility prediction framework, the short-time objective intelligibility (STOI) measure is used as an accurate and well-known method. The experimental results show a high correlation between the twin-HMM-based STOI (THMMB-STOI) and the human speech recognition results, even slightly outperforming the conventional STOI predictions computed using the actual clean reference signals.
- 1 March 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 624-628
Twin-HMM-based non-intrusive speech intelligibility prediction
Most of the objective measures employed for speech intelligibility prediction require a clean reference signal, which is not accessible in all realistic scenarios. In this paper, we propose to re-synthesize the relevant features of the clean signal using only the noisy speech signal and utilize them inside an intelligibility prediction framework which requires a reference. A statistical model called twin hidden Markov model (THMM) is used to synthesize the clean speech features. For the intelligibility prediction framework, the short-time objective intelligibility (STOI) measure is used as an accurate and well-known method. The experimental results show a high correlation between the twin-HMM-based STOI (THMMB-STOI) and the human speech recognition results, even slightly outperforming the conventional STOI predictions computed using the actual clean reference signals.
- 1 December 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Environmental sound classification using spectral dynamic features
This paper presents a novel feature extraction method for environmental sounds classification. Although many kinds of audio features have been investigated for environmental sound classification tasks, most of them have been extracted only to model the speech signal structure, which explains their lower performance when dealing with other kinds of audio signals. The method proposed in this paper processes and extracts the spectral changes throughout the frames of a sound file and appends them to the frame-based spectral feature vectors as dynamic features. Experimental results show that proposed features outperform the commonly used audio features in context recognition tasks.
- 1 December 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Environmental sound classification using spectral dynamic features
This paper presents a novel feature extraction method for environmental sounds classification. Although many kinds of audio features have been investigated for environmental sound classification tasks, most of them have been extracted only to model the speech signal structure, which explains their lower performance when dealing with other kinds of audio signals. The method proposed in this paper processes and extracts the spectral changes throughout the frames of a sound file and appends them to the frame-based spectral feature vectors as dynamic features. Experimental results show that proposed features outperform the commonly used audio features in context recognition tasks.