Automatic Speech Recognition (ASR)

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

9 leaderboard tables shown for this task, 9 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

34 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 34 until expanded.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 622 papers with code (3,012 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
  9 Apr 2018 35 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 1 pointer-only (licence)
  Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems.
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
  18 Apr 2019 30 repositories listed Syntology ran 1 of 18 samples · 17 unverified
  On LibriSpeech, we achieve 6.
• Conformer: Convolution-augmented Transformer for Speech Recognition
  16 May 2020 25 repositories listed Syntology ran 4 of 7 samples · 3 unverified · 2 pointer-only (licence)
  Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs).
• Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces
  25 May 2018 16 repositories listed Syntology ran 1 of 15 samples · 14 unverified
  This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices.
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
  7 Oct 2016 14 repositories listed Syntology ran 7 of 21 samples · 14 unverified · 6 pointer-only (licence)
  We consider the two related problems of detecting if an example is misclassified or out-of-distribution.
• SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
  14 Oct 2021 6 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for…
• ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
  7 May 2020 6 repositories listed
  We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.
• Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM
  8 Jun 2017 6 repositories listed
  The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder.
• Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models
  8 Nov 2020 5 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  To the best of our knowledge, we have achieved state-of-the-art end-to-end Transformer based model performance on Switchboard and AMI.
• Multi-blank Transducers for Speech Recognition
  4 Nov 2022 4 repositories listed
  This paper proposes a modification to RNN-Transducer (RNN-T) models for automatic speech recognition (ASR).
• Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
  2 Jun 2022 4 repositories listed Syntology ran 31 of 49 samples · 18 unverified
  After re-examining the design choices for both the macro and micro-architecture of Conformer, we propose Squeezeformer which consistently outperforms the state-of-the-art ASR models under the same training schemes.
• Multi-modal Dense Video Captioning
  17 Mar 2020 4 repositories listed
  We apply automatic speech recognition (ASR) system to obtain a temporally aligned textual description of the speech (similar to subtitles) and treat it as a separate input alongside video frames and the corresponding…
• A Simplified Fully Quantized Transformer for End-to-end Speech Recognition
  9 Nov 2019 4 repositories listed
  While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit…
• Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
  30 Oct 2018 4 repositories listed
  The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word.
• Deep Audio-Visual Speech Recognition
  6 Sep 2018 4 repositories listed
  The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio.
• Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
  5 Jan 2018 4 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  We construct targeted audio adversarial examples on automatic speech recognition.
• State-of-the-art Speech Recognition With Sequence-to-Sequence Models
  5 Dec 2017 4 repositories listed
  Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a…
• EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding
  29 Jul 2015 4 repositories listed
  The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs).
• Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
  23 Jul 2015 4 repositories listed Syntology ran 0 of 17 samples · 17 unverified
  Energy disaggregation estimates appliance-by-appliance electricity consumption from a single meter that measures the whole home's electricity demand.
• An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
  13 Feb 2024 3 repositories listed
  We found that delicate designs are not necessary, while an embarrassingly simple composition of off-the-shelf speech encoder, LLM, and the only trainable linear projector is competent for the ASR task.
• A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition
  7 Nov 2023 3 repositories listed
  We demonstrate that finetuning Conformer-transducer models on child speech yields significant improvements in ASR performance on child speech, compared to the non-finetuned models.
• ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications
  8 Nov 2022 3 repositories listed
  In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data.
• TVLT: Textless Vision-Language Transformer
  28 Sep 2022 3 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal…
• Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization
  29 Mar 2022 3 repositories listed
  First, a non-deterministic WFST outputs all normalization candidates, and then a neural language model picks the best one -- similar to shallow fusion for automatic speech recognition.
• MT3: Multi-Task Multitrack Music Transcription
  4 Nov 2021 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding.
• FAST-RIR: Fast neural diffuse room impulse response generator
  7 Oct 2021 3 repositories listed
  We present a neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
• End-to-end Audio-visual Speech Recognition with Conformers
  12 Feb 2021 3 repositories listed
  In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner.
• The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS
  6 Oct 2020 3 repositories listed
  This paper presents the sequence-to-sequence (seq2seq) baseline system for the voice conversion challenge (VCC) 2020.
• KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition
  7 Sep 2020 3 repositories listed
  Therefore, we propose preprocessing methods for KsponSpeech corpus and a baseline model for benchmarks.
• Automatic Speech Recognition Benchmark for Air-Traffic Communications
  18 Jun 2020 3 repositories listed
  We demonstrate that the cross-accent flaws due to speakers' accents are minimized due to the amount of data, making the system feasible for ATC environments.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.