Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.
AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin. The recording procedure, including audio capturing devices and environments are presented in details. The preparation of the related resources, including transcriptions and lexicon are described. The corpus is released with a Kaldi recipe. Experimental results implies that the quality of audio recordings and transcriptions are promising.
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
A survey that classifies non-intrusive ASR refinement methods into five categories, reviews domain adaptation and evaluation datasets, proposes standardized metrics, and identifies future research directions.
On-policy distillation from a Qwen-ASR teacher improves a 0.6B Ark-ASR model over supervised fine-tuning and a same-scale baseline on four of five ASR benchmarks using 100k hours of speech.
citing papers explorer
-
Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation
Agentic ASR adds closed-loop semantic correction to ASR and introduces S²ER, an LLM judge for meaning-level errors, showing larger gains on semantic than token metrics across multilingual benchmarks.
-
Non-Intrusive Automatic Speech Recognition Refinement: A Survey
A survey that classifies non-intrusive ASR refinement methods into five categories, reviews domain adaptation and evaluation datasets, proposes standardized metrics, and identifies future research directions.
-
Data-Efficient On-Policy Distillation for Automatic Speech Recognition
On-policy distillation from a Qwen-ASR teacher improves a 0.6B Ark-ASR model over supervised fine-tuning and a same-scale baseline on four of five ASR benchmarks using 100k hours of speech.