We used the training dataset provided by the "REVERB challenge" (reverberant voice enhancement and recognition benchmark) [40].
The recently released REverberant Voice Enhancement and Recognition Benchmark (REVERB) challenge includes a reverberant automatic speech recognition (ASR) task.
Taking a single-stage system as benchmark, enhancement of 35 and 33.3% is shown in the flow rate and pressure head respectively for a two-stage system.
Hence, our proposed E2M rule is an enhancement of the benchmark EXP rule, which is commonly used in LTE packet scheduling.
The REverberant Voice Enhancement and Recognition Benchmark (REVERB) challenge is an Audio and Acoustic Signal Processing (AASP) challenge sponsored by the IEEE Signal Processing Society in 2013, and has recently been released for studying reverberant speech enhancement and recognition techniques [1].
This paper presents extended techniques aiming at the improvement of automatic speech recognition (ASR) in single-channel scenarios in the context of the REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge.
Here too, we see that there is a significant enhancement to the benchmark, and that the precision improvement curves are not equal for the different elapsed time parameters, meaning that different time scales bring different information.
In order to provide a common evaluation framework for developing and testing of algorithms in the fields of dereverberation as well as reverberation-robust ASR, the REverberant Voice Enhancement and Recognition Benchmark (REVERB) challenge [8] has been launched and REVERB contributions showed significant improvements for speech enhancement (cf., e.g., [9]) and ASR (cf., e.g., [10, 11]).
In recent years, substantial progress has been made for distant/reverberant speech recognition by several important challenges, such as REVERB (REverberant Voice Enhancement and Recognition Benchmark) challenge [3], CHiME [4] challenge mainly for solving background noises, and ASpIRE (Automatic Speech Recognition In Reverberant Environments) [5].
UCPMOT + NF_N + MOT show specific bordering enhancement compared to the benchmarking techniques (SMOTE, Borderline-SMOTE, ADASYN and SMOTEBoost).
Laurie Harbour-Felax has more than 21 years of experience providing the automotive industry with benchmarking, manufacturing assessments, performance enhancement and strategic planning.
