SOTAVerified

Speech Recognition

Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.

( Image credit: SpecAugment )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1101–1150 of 6433 papers

TitleStatusHype
Boosting Code-Switching ASR with Mixture of Experts Enhanced Speech-Conditioned LLM—0
Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error CorrectionCode0
Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition—0
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder—0
Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection—0
A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering—0
LM-assisted keyword biasing with Aho-Corasick algorithm for Transducer-based ASR—0
Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper—0
Large Language Model Should Understand Pinyin for Chinese ASR Error Correction—0
Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space—0
Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech RecognitionCode0
Personalized Speech Recognition for Children with Test-Time Adaptation—0
Robust Audiovisual Speech Recognition Models with Mixture-of-Experts—0
ASR Benchmarking: Need for a More Representative Conversational DatasetCode0
META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR—0
WER We Stand: Benchmarking Urdu ASR Models—0
Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text—0
Chain-of-Thought Prompting for Speech Translation—0
A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework—0
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses—0
Zero Shot Text to Speech Augmentation for Automatic Speech Recognition on Low-Resource Accented Speech Corpora—0
Bio-Inspired Mamba: Temporal Locality and Bioplausible Learning in Selective State Space Models—0
Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models—0
An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems—0
Augmenting Automatic Speech Recognition Models with Disfluency Detection—0
A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models—0
SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition—0
Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition—0
ASR Error Correction using Large Language Models—0
Exploring SSL Discrete Tokens for Multilingual ASR—0
LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation—0
Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech—0
NEST-RQ: Next Token Prediction for Speech Self-Supervised Pre-Training—0
CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments—0
Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?—0
Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages—0
Clean Label Attacks against SLU Systems—0
Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction—0
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion ModelsCode0
Full-text Error Correction for Chinese Speech Recognition with Large Language Model—0
The Faetar Benchmark: Speech Recognition in a Very Under-Resourced Language—0
Faster Speech-LLaMA Inference with Multi-token Prediction—0
Contextualization of ASR with LLM using phonetic retrieval-based augmentation—0
Enhancing CTC-Based Visual Speech Recognition—0
Linear Time Complexity Conformers with SummaryMixing for Streaming Speech RecognitionCode0
Rethinking Mamba in Speech Processing by Self-Supervised Models—0
How Redundant Is the Transformer Stack in Speech Representation Models?—0
An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognition—0
Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking—0
Advancing Topic Segmentation of Broadcasted Speech with Multilingual Semantic EmbeddingsCode0
Show:102550
← PrevPage 23 of 129Next →
All datasetsLibriSpeech test-cleanLibriSpeech test-otherSwitchboard + Hub500TIMITAISHELL-1WSJ eval92Common Voice Germanswb_hub_500 WER fullSWBCHTUDACommon Voice FrenchCommon Voice SpanishMediaSpeech

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AmNetWord Error Rate (WER)8.6—Unverified
2HMM-(SAT)GMMWord Error Rate (WER)8—Unverified
3Local Prior Matching (Large Model)Word Error Rate (WER)7.19—Unverified
4SnipsWord Error Rate (WER)6.4—Unverified
5Li-GRUWord Error Rate (WER)6.2—Unverified
6HMM-DNN + pNorm*Word Error Rate (WER)5.5—Unverified
7CTC + policy learningWord Error Rate (WER)5.42—Unverified
8Deep Speech 2Word Error Rate (WER)5.33—Unverified
9HMM-TDNN + iVectorsWord Error Rate (WER)4.8—Unverified
10Gated ConvNetsWord Error Rate (WER)4.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Local Prior Matching (Large Model)Word Error Rate (WER)20.84—Unverified
2SnipsWord Error Rate (WER)16.5—Unverified
3Local Prior Matching (Large Model, ConvLM LM)Word Error Rate (WER)15.28—Unverified
4Deep Speech 2Word Error Rate (WER)13.25—Unverified
5TDNN + pNorm + speed up/down speechWord Error Rate (WER)12.5—Unverified
6CTC-CRF 4gram-LMWord Error Rate (WER)10.65—Unverified
7Convolutional Speech RecognitionWord Error Rate (WER)10.47—Unverified
8MT4SSLWord Error Rate (WER)9.6—Unverified
9Jasper DR 10x5Word Error Rate (WER)8.79—Unverified
10EspressoWord Error Rate (WER)8.7—Unverified
#ModelMetricClaimedVerifiedStatus
1Deep SpeechPercentage error20—Unverified
2DNN-HMMPercentage error18.5—Unverified
3CD-DNNPercentage error16.1—Unverified
4DNNPercentage error16—Unverified
5DNN + DropoutPercentage error15—Unverified
6DNN BMMIPercentage error12.9—Unverified
7DNN MPEPercentage error12.9—Unverified
8DNN MMIPercentage error12.9—Unverified
9HMM-TDNN + pNorm + speed up/down speechPercentage error12.9—Unverified
10HMM-DNN +sMBRPercentage error12.6—Unverified
#ModelMetricClaimedVerifiedStatus
1LSNNPercentage error33.2—Unverified
2LAS multitask with indicators samplingPercentage error20.4—Unverified
3Soft Monotonic Attention (ours, offline)Percentage error20.1—Unverified
4QCNN-10L-256FMPercentage error19.64—Unverified
5Bi-LSTM + skip connections w/ CTCPercentage error17.7—Unverified
6Bi-RNN + AttentionPercentage error17.6—Unverified
7RNN-CRF on 24(x3) MFSCPercentage error17.3—Unverified
8CNN in time and frequency + dropout, 17.6% w/o dropoutPercentage error16.7—Unverified
9Light Gated Recurrent UnitsPercentage error16.7—Unverified
10GRUPercentage error16.6—Unverified
#ModelMetricClaimedVerifiedStatus
1AttWord Error Rate (WER)18.7—Unverified
2CTC/AttWord Error Rate (WER)6.7—Unverified
3BRA-EWord Error Rate (WER)6.63—Unverified
4CTC-CRF 4gram-LMWord Error Rate (WER)6.34—Unverified
5BATWord Error Rate (WER)4.97—Unverified
6ParaformerWord Error Rate (WER)4.95—Unverified
7U2Word Error Rate (WER)4.72—Unverified
8UMAWord Error Rate (WER)4.7—Unverified
9Lightweight TransducerWord Error Rate (WER)4.31—Unverified
10CIF-HKD With LMWord Error Rate (WER)4.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Jasper 10x3Word Error Rate (WER)6.9—Unverified
2CNN over RAW speech (wav)Word Error Rate (WER)5.6—Unverified
3CTC-CRF 4gram-LMWord Error Rate (WER)3.79—Unverified
4Deep Speech 2Word Error Rate (WER)3.6—Unverified
5test-set on open vocabulary (i.e. harder), model = HMM-DNN + pNorm*Word Error Rate (WER)3.6—Unverified
6Convolutional Speech RecognitionWord Error Rate (WER)3.5—Unverified
7TC-DNN-BLSTM-DNNWord Error Rate (WER)3.5—Unverified
8EspressoWord Error Rate (WER)3.4—Unverified
9CTC-CRF VGG-BLSTMWord Error Rate (WER)3.2—Unverified
10Transformer with Relaxed AttentionWord Error Rate (WER)3.19—Unverified