https://github.com/backspacetg/distilxlsr
공식 코드DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model
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/backspacetg/simul_whisper
공식 코드Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection
https://github.com/badripatro/mamba360
공식 코드https://github.com/bagustris/A-VB2022_CCC
공식 코드Predicting Affective Vocal Bursts with Finetuned wav2vec 2.0
https://github.com/balaji1312/chser
공식 코드CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASR
https://github.com/balaji1312/sa_merging
공식 코드Selective Attention Merging for low resource tasks: A case study of Child ASR
https://github.com/bartelds/asr-augmentation
공식 코드https://github.com/bartwojcik/adaptive_computation_modules
공식 코드Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
https://github.com/bbc/bbc-speech-segmenter
공식 코드X-Vector based voice activity detection for multi-genre broadcast speech-to-text
https://github.com/beer-asr/beer
공식 코드Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units
https://github.com/bepierre/SpeechVGG
공식 코드Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing
https://github.com/besacier/AMMIcourse
공식 코드Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning
https://github.com/bfs18/rfwave
공식 코드RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
https://github.com/bfs18/tacotron2
공식 코드https://github.com/bloodraven66/ssl_aai
공식 코드https://github.com/boknilev/asr-repr-analysis
공식 코드Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems
https://github.com/bolajiy/golden-retriever
공식 코드End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representations
https://github.com/bonaventuredossou/active_learning_african_asr
공식 코드https://github.com/bonaventuredossou/fonasr
공식 코드https://github.com/bootphon/articulatory_inversion
공식 코드Independent and automatic evaluation of acoustic-to-articulatory inversion models
https://github.com/borrisonxiao/icefall
공식 코드HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
https://github.com/bosecorp/devo
공식 코드Self-Supervised Learning for Speech Enhancement through Synthesis
https://github.com/bpopeters/mg2p
공식 코드Massively Multilingual Neural Grapheme-to-Phoneme Conversion
https://github.com/briansidp/espnet
공식 코드End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator
https://github.com/briansidp/whisperbiasing
공식 코드Can Contextual Biasing Remain Effective with Whisper and GPT-2?
https://github.com/brkljac/videoface2.0
공식 코드https://github.com/burchim/avec
공식 코드Audio-Visual Efficient Conformer for Robust Speech Recognition
https://github.com/burchim/efficientconformer
공식 코드Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition
https://github.com/butspeechfit/diacorrect
공식 코드DiaCorrect: Error Correction Back-end For Speaker Diarization
https://github.com/bytedance/lightseq
공식 코드LightSeq2: Accelerated Training for Transformer-based Models on GPUs
https://github.com/bytedance/salmonn
공식 코드SALMONN: Towards Generic Hearing Abilities for Large Language Models
https://github.com/bzhangGo/zero
공식 코드Revisiting End-to-End Speech-to-Text Translation From Scratch
https://github.com/c3imaging/child_asr_conformer
공식 코드https://github.com/c3imaging/child_tts_fastpitch
공식 코드Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning
https://github.com/c3imaging/whisper_child_speech
공식 코드https://github.com/cactuswiththoughts/unsupasrtheory
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.