https://github.com/tomohikonakamura/ica_dsu_espnet
공식 코드Discrete Speech Unit Extraction via Independent Component Analysis
Papers with Code 아카이브
Speech Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 236
- 보존된 평가 기록
- 398
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.
<span style="color:grey; opacity: 0.6">( Image credit: SpecAugment )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tonychenxyz/emoknob
공식 코드EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control
https://github.com/tpekarekrosin/uhh_ub_ageawarehri
공식 코드A Framework for Adapting Human-Robot Interaction to Diverse User Groups
https://github.com/tran-khoa/joint-training-cascaded-st
공식 코드Does Joint Training Really Help Cascaded Speech Translation?
https://github.com/trangham283/asr_preps
공식 코드Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts
https://github.com/transfer-learning-asr/transfer-learning-asr
공식 코드https://github.com/trikaldarshi/score_finetuning
공식 코드SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations
https://github.com/tstafylakis/Lipreading-ResNet
공식 코드https://github.com/tts-tutorial/survey
공식 코드https://github.com/ttslr/strengthnet
공식 코드StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis
https://github.com/turinaf/sagalee
공식 코드Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language
https://github.com/tushartalukder/bengali-asr-model-using-wav2vec2
공식 코드An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer Learning
https://github.com/tvanh512/importantAug
공식 코드https://github.com/tzyll/ChineseHP
공식 코드Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models
https://github.com/ubc-nlp/l2asr
공식 코드https://github.com/ucla-trustworthy-ai-lab/autodiffusion
공식 코드AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
https://github.com/ufal/whisper_streaming
공식 코드https://github.com/ugurtegin/Nonlinear_MMF_Network
공식 코드https://github.com/uhh-lt/kaldi-tuda-de
공식 코드https://github.com/uirlx/dialogueagents
공식 코드DialogueAgents: A Hybrid Agent-Based Speech Synthesis Framework for Multi-Party Dialogue
https://github.com/ujjwal-9/celestini-dl
공식 코드Indian EmoSpeech Command Dataset: A dataset for emotion based speech recognition in the wild
https://github.com/umassos/flowsense
공식 코드FlowSense: Monitoring Airflow in Building Ventilation Systems Using Audio Sensing
https://github.com/umbertocappellazzo/llama-avsr
공식 코드Large Language Models are Strong Audio-Visual Speech Recognition Learners
https://github.com/unza-speech-lab/zambezi-voice
공식 코드Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages
https://github.com/usefulsensors/moonshine
공식 코드Moonshine: Speech Recognition for Live Transcription and Voice Commands
https://github.com/utter-project/elitr-bench
공식 코드ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models
https://github.com/uva-dsa/ems-pipeline
공식 코드Real-Time Multimodal Cognitive Assistant for Emergency Medical Services
https://github.com/uwjunqi/Subrank
공식 코드Unsupervised Submodular Rank Aggregation on Score-based Permutations
https://github.com/v-andrearczyk/caffe-TCNN
공식 코드Using Filter Banks in Convolutional Neural Networks for Texture Classification
https://github.com/v-iashin/MDVC
공식 코드https://github.com/vectominist/spin
공식 코드Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering
https://github.com/villawang/Neuro-AI-Interface
공식 코드Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
https://github.com/vinairesearch/phowhisper
공식 코드https://github.com/vineet2104/adversarialtrainingfordisfluencycorrection
공식 코드https://github.com/vineet2104/disco
공식 코드DISCO: A Large Scale Human Annotated Corpus for Disfluency Correction in Indo-European Languages
https://github.com/vita-mllm/vita-audio
공식 코드VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.