Papers with Code 아카이브

Speech Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/pwwl/enhanced-binary-diversification

공식 코드

Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes

https://github.com/pyf98/NeMo_VoiceTextBlender

공식 코드

VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning

https://github.com/pytorch/audio

공식 코드

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

https://github.com/pytorch/fairseq

공식 코드

wav2vec: Unsupervised Pre-training for Speech Recognition

https://github.com/pytorch/fairseq/blob/f3b6f5817fbee59057ae2506f01502ea3c301b4b/examples/wav2vec/README.md

공식 코드

Self-training and Pre-training are Complementary for Speech Recognition

https://github.com/pytorch/fairseq/tree/main/examples/data2vec

공식 코드

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text

공식 코드

fairseq S2T: Fast Speech-to-Text Modeling with fairseq

https://github.com/pzelasko/kaldi

공식 코드

How Phonotactics Affect Multilingual and Zero-shot ASR Performance

https://github.com/qas-lab/barovicreu

공식 코드

TinyML for Speech Recognition

https://github.com/qcri/dialectID

공식 코드

Speech Recognition Challenge in the Wild: Arabic MGB-3

https://github.com/qcri/e-wer

공식 코드

Word Error Rate Estimation Without ASR Output: e-WER2

https://github.com/qiaoqiao2323/robot-speech-intelligibility

공식 코드

No More Mumbles: Enhancing Robot Intelligibility through Speech Adaptation

https://github.com/qiujiali/lattice-rescore

공식 코드

Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition

https://github.com/qiujiali/lattice_rnn

공식 코드

Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation

https://github.com/qmgzhao/pqm

공식 코드

Enhancing Quantised End-to-End ASR Models via Personalisation

https://github.com/quanpn90/NMTGMinor

공식 코드

Adapting End-to-End Speech Recognition for Readable Subtitles

https://github.com/qwenlm/qwen-audio

공식 코드

Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

https://github.com/r9y9/wavenet_vocoder

공식 코드

ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit

https://github.com/racai-ai/robinasr

공식 코드

Romanian Speech Recognition Experiments from the ROBIN Project

https://github.com/rafa-zy/sent

공식 코드

Learning to Detect Noisy Labels Using Model-Based Features

https://github.com/raianand1991/tie

공식 코드

A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videos

https://github.com/rainavyas/prepend_acoustic_attack

공식 코드

Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models

https://github.com/rainbowluocs/openomni

공식 코드

OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis

https://github.com/raminmh/liquid-s4

공식 코드

Liquid Structural State-Space Models

https://github.com/raotnameh/End-to-end-E2E-Named-Entity-Recognition-from-English-Speech

공식 코드

End-to-end Named Entity Recognition from English Speech

https://github.com/raphaelolivier/robust_speech

공식 코드

Recent improvements of ASR models in the face of adversarial attacks

https://github.com/raphaelolivier/smoothingasr

공식 코드

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition

https://github.com/raphaelolivier/whisper_attack

공식 코드

There is more than one kind of robustness: Fooling Whisper with adversarial examples

https://github.com/reddragon/efficient-dl-survey-paper

공식 코드

Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better

https://github.com/redmist328/apnet2

공식 코드

APNet2: High-quality and High-efficiency Neural Vocoder with Direct Prediction of Amplitude and Phase Spectra

https://github.com/redwankarimsony/weightperturbation-msu

공식 코드

Investigating Weight-Perturbed Deep Neural Networks With Application in Iris Presentation Attack Detection

https://github.com/revdotcom/speech-datasets

공식 코드

Earnings-22: A Practical Benchmark for Accents in the Wild

https://github.com/rf5/simple-asgan

공식 코드

GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models

https://github.com/rf5/transfusion-asr

공식 코드

TransFusion: Transcribing Speech with Multinomial Diffusion

https://github.com/rhoposit/icassp2021

공식 코드

Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm

https://github.com/rickltt/punctuation_restoration

공식 코드

A Small and Fast BERT for Chinese Medical Punctuation Restoration

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.