Aishell-1

The AISHELL-1 dataset is a benchmark for evaluating automatic speech recognition (ASR) systems, specifically focusing on their performance in recognizing and correcting named entities.

Papers using Aishell-1 (76)

PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition2025 · 1 citesBreaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition2025 · 1 citesJSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASR2026Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction2026IKFST: IOO and KOO Algorithms for Accelerated and Precise WFST-based End-to-End Automatic Speech Recognition2026Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization2026End-to-end Speech Recognition with similar length speech and text2025A Bottom-up Framework with Language-universal Speech Attribute Modeling for Syllable-based ASR2025Objective Soups: Multilingual Multi-Task Modeling for Speech Processing2025IML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech Processing2025CR-CTC: Consistency regularization on CTC for improved speech recognition2024M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper2024EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed2024Zipformer: A faster and better encoder for automatic speech recognition2023 · 28 citesImproving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models2022 · 24 citesExploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study2023 · 15 citesUnveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasets2024 · 12 citesImproving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model2021 · 6 citesMulti-Level Modeling Units for End-to-End Mandarin Speech Recognition2022 · 4 citesSpeaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker Extraction2022 · 3 citesNextformer: A ConvNeXt Augmented Conformer For End-To-End Speech Recognition2022 · 3 citesImproving Mandarin Speech Recogntion with Block-augmented Transformer2022 · 3 citesConsistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMI2021 · 2 citesParaformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition2022 · 2 citesTowards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation2022 · 2 citesUniEnc-CASSNAT: An Encoder-only Non-autoregressive ASR for Speech SSL Models2024 · 2 citesEfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization2024 · 2 citesDecoupling recognition and transcription in Mandarin ASR2021 · 1 citesNon-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition2021 · 1 citesOn the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR2022 · 1 citesTransformer-based Streaming ASR with Cumulative Attention2022 · 1 citesImproving CTC-based ASR Models with Gated Interlayer Collaboration2022 · 1 citesLinguistic-Enhanced Transformer with CTC Embedding for Speech Recognition2022 · 1 citesConformer-based End-to-end Speech Recognition With Rotary Position Embedding2021Cross-domain Single-channel Speech Enhancement Model with Bi-projection Fusion Module for Noise-robust ASR2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition2021Improving CTC-based speech recognition via knowledge transferring from pre-trained language models2022Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASR2022CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR2022An Empirical Study of Language Model Integration for Transducer based Speech Recognition2022Memory-Efficient Training of RNN-Transducer with Sampled Softmax2022A CTC Triggered Siamese Network with Spatial-Temporal Dropout for Speech Recognition2022Knowledge Transfer and Distillation from Autoregressive to Non-Autoregressive Speech Recognition2022PSVRF: Learning to restore Pitch-Shifted Voice without reference2022A context-aware knowledge transferring strategy for CTC-based ASR2022SAN: a robust end-to-end ASR model architecture2022Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames2022Improving Noisy Student Training on Non-target Domain Data for Automatic Speech Recognition2022SSCFormer: Push the Limit of Chunk-wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution2022Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation2023Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition2023Pyramid Multi-branch Fusion DCNN with Multi-Head Self-Attention for Mandarin Speech Recognition2023Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition2023A Lexical-aware Non-autoregressive Transformer-based ASR Model2023GNCformer Enhanced Self-attention for Automatic Speech Recognition2023Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding2023Enhancing the Unified Streaming and Non-streaming Model with Contrastive Learning2023Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure2023TST: Time-Sparse Transducer for Automatic Speech Recognition2023CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition2023ApproBiVT: Lead ASR Models to Generalize Better Using Approximated Bias-Variance Tradeoff Guided Early Stopping and Checkpoint Averaging2023HypR: A comprehensive study for ASR hypothesis revising with a reference corpus2023Cross-modal Alignment with Optimal Transport for CTC-based ASR2023Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR2023Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognition2024Multi-Channel Multi-Speaker ASR Using Target Speaker's Solo Segment2024Streaming Decoder-Only Automatic Speech Recognition with Discrete Speech Units: A Pilot Study2024CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer based Streaming ASR2024HydraFormer: One Encoder For All Subsampling Rates2024An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognition2024Large Language Model Should Understand Pinyin for Chinese ASR Error Correction2024Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs2024Deep CLAS: Deep Contextual Listen, Attend and Spell2024Sample adaptive data augmentation with progressive scheduling2024Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model2022UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction2024