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/kexinhuang19/instructttseval
공식 코드https://github.com/kgnlp/allophant
공식 코드Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes
https://github.com/khassanoff/SG_streets
공식 코드Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation
https://github.com/khfs/DuplexMamba
공식 코드DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities
https://github.com/kjw11/csenet-asr
공식 코드Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
https://github.com/kjw11/speaker-aware-ctc
공식 코드Disentangling Speakers in Multi-Talker Speech Recognition with Speaker-Aware CTC
https://github.com/knoriy/emns-dct
공식 코드https://github.com/knowledgetechnologyuhh/meld-fair
공식 코드Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge
https://github.com/koenecke/auditing_asr_aphasia
공식 코드https://github.com/koenecke/hallucination_harms
공식 코드https://github.com/komyeongjin/specdiff-gan
공식 코드https://github.com/kssteven418/squeezeformer
공식 코드Squeezeformer: An Efficient Transformer for Automatic Speech Recognition
https://github.com/kttrcdl/umetts
공식 코드UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts
https://github.com/kyutai-labs/moshi
공식 코드Moshi: a speech-text foundation model for real-time dialogue
https://github.com/lallubharteja/KWS-Scripts
공식 코드Subword RNNLM Approximations for Out-Of-Vocabulary Keyword Search
https://github.com/lchen001/hapi
공식 코드HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions
https://github.com/leduckhai/multimed
공식 코드https://github.com/leduckhai/sentiment-reasoning
공식 코드https://github.com/leduckhai/wav2graph
공식 코드wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech
https://github.com/lee-jhwn/is25-emg-ema
공식 코드Articulatory Feature Prediction from Surface EMG during Speech Production
https://github.com/lessw2020/fadam_pytorch
공식 코드FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
https://github.com/linguisticanomalies/paradox-asr
공식 코드https://github.com/litterbrother-xiao/overview-of-non-autoregressive-applications
공식 코드A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
https://github.com/liu12366262626/alignvsr
공식 코드AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition
https://github.com/liuxubo717/sound_generation
공식 코드Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning
https://github.com/liuzhuang13/DenseNet
공식 코드https://github.com/ljuvela/ResGAN
공식 코드Speech waveform synthesis from MFCC sequences with generative adversarial networks
https://github.com/ljuvela/collaborative-watermarking-with-codecs
공식 코드Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis
https://github.com/lliar-liar/daily-omni
공식 코드Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities
https://github.com/lorenlugosch/conditional-computation-using-surprisal
공식 코드Surprisal-Triggered Conditional Computation with Neural Networks
https://github.com/lorenlugosch/end-to-end-SLU
공식 코드Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models
https://github.com/louislau1129/comflp
공식 코드CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning
https://github.com/lucasgris/wav2vec4bp
공식 코드https://github.com/lucasnfe/adl-piano-midi
공식 코드https://github.com/lucasnfe/bardo-composer
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.