IEEE Recommended Practice for Speech Quality Measurements

1969

Citations in the corpus

• Time-Frequency Masking in the Complex Domain for Speech Dereverberation and Denoising (2017, positive): “We use the IEEE corpus [17] to train and test our system.”
• Subjective Comparison of Speech Enhancement Algorithms (2006, background): “The noisy database contains 30 IEEE sentences [2] produced by three male and three female speakers, and was corrupted by eight different real-world noises at different SNRs.”
• Robustness of speech quality metrics to background noise and network degradations: Comparing ViSQOL, PESQ and POLQA (2013, unknown): “3697978-1-4799-0356-6/13/$31.00 ©2013 IEEE ICASSP 2013”
• Learning Spectral Mapping for Speech Dereverberation and Denoising (2015, methodology): “We use 200 anechoic female utterances from the IEEE corpus [12] to form the training set.”
• Speech Quality Assessment (2011, methodology): “This method is one of the methods recommended by the IEEE Subcommittee on Subjective Methods [7] as well as by ITU [6,8].”
• DNN-based stochastic postfilter for HMM-based speech synthesis (2014, methodology): “The sentences were chosen from the first 12 sets of the Harvard dataset [18].”
• A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation (2010, methodology): “A very recent study [20] has successfully applied the tandem algorithm to pitch tracking for segregating the IEEE sentences [22] without any retraining or change.”
• Cocktail Party Processing via Structured Prediction (2012, methodology): “1 Experimental setup Our training and test sets are primarily created from the IEEE corpus [24] recorded by a single female speaker.”
• A New Framework for CNN-Based Speech Enhancement in the Time Domain (2019, unknown): “dependent way on the IEEE database[33].”
• RUSLAN: Russian Spoken Language Corpus for Speech Synthesis (2019, methodology): “This method is recommended by ITU and IEEE for the quality estimation of the synthesized speech [14,19].”
• Exploring Monaural Features for Classification-Based Speech Segregation (2013, methodology): “1 Experimental Setup We use the IEEE corpus [15] for all of our evaluations.”