Aishell-1
PulseAugur coverage of Aishell-1 — every cluster mentioning Aishell-1 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Bio-inspired Spiking Ternary GRU achieves competitive speech recognition
Researchers have developed a novel Spiking Ternary GRU (stGRU) architecture inspired by the human cerebral cortex for improved speech recognition. This bio-inspired model couples parallel resonate-and-fire dynamics with…
-
New HearInContext benchmark tests speech recognition's grasp of implicit context
Researchers have introduced HearInContext, a new benchmark designed to evaluate the ability of speech recognition systems to understand implicit context. This benchmark, which includes 3,764 semantic test cases focusing…
-
New X2Streaming-ASR system slashes speech recognition latency
Researchers have developed X2Streaming-ASR, a novel system for streaming automatic speech recognition (ASR) designed for real-time applications. Unlike existing methods that use fixed chunk sizes or target delays, X2Str…
-
New Latent Softmax improves multilingual ASR data efficiency
Researchers have developed a new output layer called Latent Softmax for multilingual automatic speech recognition (ASR) systems. This method aims to improve data efficiency by better handling the differing supervision g…
-
New PERL model enhances Chinese ASR error correction with phonetic and semantic fusion
Researchers have developed PERL, a new language model designed to correct errors in Chinese Automatic Speech Recognition (ASR) systems. PERL addresses the challenge of phonetic errors and length constraints by employing…