SOTAVerified

Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 601–650 of 3012 papers

TitleStatusHype
A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks—0
A GEN AI Framework for Medical Note Generation—0
ASR-based Features for Emotion Recognition: A Transfer Learning Approach—0
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition—0
AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents—0
Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio—0
Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model—0
ASR-based CALL systems and learner speech data: new resources and opportunities for research and development in second language learning—0
ASR-Aware End-to-end Neural Diarization—0
AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition—0
ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognition—0
Automatic Speech Recognition Advancements for Indigenous Languages of the Americas—0
Afrispeech-Dialog: A Benchmark Dataset for Spontaneous English Conversations in Healthcare and Beyond—0
Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech—0
ASR Adaptation for E-commerce Chatbots using Cross-Utterance Context and Multi-Task Language Modeling—0
A Speech Test Set of Practice Business Presentations with Additional Relevant Texts—0
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR—0
Ask2Mask: Guided Data Selection for Masked Speech Modeling—0
AfriNames: Most ASR models "butcher" African Names—0
Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition—0
Comparative Analysis of the wav2vec 2.0 Feature Extractor—0
A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data—0
A Corpus of Read and Spontaneous Upper Saxon German Speech for ASR Evaluation—0
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition—0
Chinese Medical Speech Recognition with Punctuated Hypothesis—0
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding—0
Accented Speech Recognition Inspired by Human Perception—0
Affect Recognition in Conversations Using Large Language Models—0
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding—0
100,000 Podcasts: A Spoken English Document Corpus—0
A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts—0
Challenges of Applying Automatic Speech Recognition for Transcribing EU Parliament Committee Meetings: A Pilot Study—0
Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition—0
CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice—0
Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks—0
Comparing Apples to Oranges: LLM-powered Multimodal Intention Prediction in an Object Categorization Task—0
Comparing Discrete and Continuous Space LLMs for Speech Recognition—0
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR—0
Challenges in Speech Recognition and Translation of High-Value Low-Density Polysynthetic Languages—0
Challenges of Computational Processing of Code-Switching—0
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech—0
AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection—0
Characterizing Audio Adversarial Examples Using Temporal Dependency—0
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement—0
A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech—0
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides—0
Challenges and Opportunities of Speech Recognition for Bengali Language—0
A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking—0
Challenges and Opportunities in Multi-device Speech Processing—0
Chain-of-Thought Prompting for Speech Translation—0
Show:102550
← PrevPage 13 of 61Next →
All datasetsLRS2RealMANSagaleeHUI speech corpusLRS3-TEDM-AILabs speech datasetThe Spoken Wikipedia CorporaVoxforge GermanVoxPopuli

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TM-CTCTest WER10.1—Unverified
2TM-seq2seqTest WER9.7—Unverified
3CTC/attentionTest WER8.2—Unverified
4LF-MMI TDNNTest WER6.7—Unverified
5Whisper-LLaMATest WER6.6—Unverified
6End2end ConformerTest WER3.9—Unverified
7End2end ConformerTest WER3.7—Unverified
8MoCo + wav2vec (w/o extLM)Test WER2.7—Unverified
9CTC/AttentionTest WER1.5—Unverified
10WhisperTest WER1.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SpatialNetCER14.5—Unverified
2CleanMel-L-maskCER14.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerTest WER15.32—Unverified
2Whisper-largev3-finetunedTest WER10.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)1.89—Unverified
#ModelMetricClaimedVerifiedStatus
1DistillAVWER1.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)4.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)8.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)3.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer Transducer (German)WER (%)8.98—Unverified