Automatic speech recognition and speech variability: A review

By Mohamed Benzeghiba, R. Mori, Olivier Deroo, Stéphane Dupont, T. Erbes, Denis Jouvet, L. Fissore, Pietro Laface, Alfred Mertins, C. Ris and 3 more. 2007

590 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ne Luo
2. Wubo Li
3. Wei Zou
4. Dongwei Jiang
5. Xiangang Li
6. Samuli Laine
7. Timo Aila
8. Abdulbasit K. Al-Talabani

In Experimental and Cognitive Psychology

1. Ryan Shaun Joazeiro de Baker
2. Joel Shor

In Speech & Audio

1. Ne Luo
2. Wubo Li
3. Xiangang Li
4. Wei Zou
5. Dongwei Jiang
6. Manoj Plakal
7. Hung-yi Lee

In Signal Processing

1. Ne Luo
2. Wubo Li
3. Wei Zou
4. Dongwei Jiang
5. Xiangang Li
6. Abdulbasit K. Al-Talabani
7. Timo Aila
8. Manoj Plakal

Citations in the corpus

• Improving Transformer-based Speech Recognition Using Unsupervised Pre-training (2019, background): “Apart from speaking style, other speech variabilities like speaking environment, speech scenarios and regional dialect [26, 30, 31] also have an impact on the performance of speech recognition system.”
• Audio-driven facial animation by joint end-to-end learning of pose and emotion (2017, methodology): “Our approach differs from most of the previous work on speech recognition, where the analysis step is typically based on a specialized techniques such as Mel-frequency cepstral coefficients (MFCC), perceptual linear prediction (PLP), and rasta filtering [Benzeghiba et al. 2007].”
• Mel Frequency Cepstral Coefficient and its Applications: A Review (2022, background): “Secondly, the analysis window can span the transition between two QSSs and the MFCC vectors extracted from such transition segments do not provide the information about a single unique (stationary) class which may lead to poor discrimination in a pattern recognition problem [9].”
• Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases (2021, background): “Automatic classification of impaired speech could also play a critical role in reducing the performance gap in automatic speech recognition (ASR) between typical and disordered speech [8, 9].”
• Algorithmic Bias in Education (2021, background): “, 2020). In these cases, finding an alternate variable to predict -- one not as impacted by bias -- may be the best alternative. In other cases, the measurement bias may emerge when human coders label data that has already been collected, a step in the pipeline which it is easier to exert control ov”