Papers with Code 아카이브
Automatic Speech Recognition (ASR)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 9
- 보존된 평가 기록
- 20
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/mtran14/dp_w2v2
공식 코드A Speech Representation Anonymization Framework via Selective Noise Perturbation
https://github.com/myHaiven/data-collection
공식 코드BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition
https://github.com/mynlp/speechparser
공식 코드https://github.com/n8rob/multilingual_tts_augmentation
공식 코드https://github.com/natsuooo/llm-ger
공식 코드LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Context
https://github.com/navana-tech/baseline_recipe_is21s_indic_asr_challenge
공식 코드Multilingual and code-switching ASR challenges for low resource Indian languages
https://github.com/naver-ai/usdm
공식 코드Paralinguistics-Aware Speech-Empowered Large Language Models for Natural Conversation
https://github.com/naver/multilingual-distilwhisper
공식 코드https://github.com/nelfproject/NeLF_Transcription_ASR
공식 코드Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling
https://github.com/nesl/adversarial_audio
공식 코드Did you hear that? Adversarial Examples Against Automatic Speech Recognition
https://github.com/niger-volta-lti/yoruba-voice
공식 코드https://github.com/nii-yamagishilab/AfriHuBERT
공식 코드AfriHuBERT: A self-supervised speech representation model for African languages
https://github.com/nilc-nlp/coraa
공식 코드https://github.com/nilc-nlp/nurc-sp
공식 코드Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models
https://github.com/nttcslab-sp-admin/tedsummary
공식 코드Attention-based Multi-hypothesis Fusion for Speech Summarization
https://github.com/ofa-sys/air-bench
공식 코드AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension
https://github.com/ofa-sys/ofa
공식 코드MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition
https://github.com/onnoeberhard/deepspeech
공식 코드Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages
https://github.com/open-speech-ekstep/indic-punct
공식 코드https://github.com/orange-opensource/olisia-dstc11
공식 코드https://github.com/osu-starlab/beavertalk
공식 코드BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System
https://github.com/pariajm/e2e-asr-and-disfluency-removal-evaluator
공식 코드https://github.com/pengchengguo/espnet
공식 코드Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain
https://github.com/pgurunath/confusion2vec_2.0
공식 코드Confusion2vec 2.0: Enriching Ambiguous Spoken Language Representations with Subwords
https://github.com/pgurunath/slu_confusion2vec
공식 코드https://github.com/pytorch/fairseq
공식 코드https://github.com/pzelasko/kaldi
공식 코드How Phonotactics Affect Multilingual and Zero-shot ASR Performance
https://github.com/qcri/e-wer
공식 코드https://github.com/qiujiali/lattice-rescore
공식 코드Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition
https://github.com/qiujiali/lattice_rnn
공식 코드Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
https://github.com/qmgzhao/pqm
공식 코드Enhancing Quantised End-to-End ASR Models via Personalisation
https://github.com/quanpn90/NMTGMinor
공식 코드Adapting End-to-End Speech Recognition for Readable Subtitles
https://github.com/qwenlm/qwen-audio
공식 코드Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
https://github.com/r9y9/wavenet_vocoder
공식 코드ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
https://github.com/raianand1991/tie
공식 코드A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.