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/MattSegal/speech-enhancement

Improved Speech Enhancement with the Wave-U-Net

https://github.com/Mayurji/Image-Classification-PyTorch

Densely Connected Convolutional Networks

https://github.com/MichaelisTrofficus/spec_augment

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

https://github.com/Microsoft/NPMT

Sequence Modeling via Segmentations

https://github.com/Mind23-2/MindCode-101/tree/main/IntegralNeuralNetworks

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

https://github.com/Mind23-2/MindCode-3/tree/main/IntegralNeuralNetworks

fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit

https://github.com/MindCode-4/code-1/tree/main/tvlt

TVLT: Textless Vision-Language Transformer

https://github.com/MindCode-4/code-1/tree/main/unispeech_sat

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

https://github.com/MindCode-4/code-1/tree/main/univnet

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

https://github.com/MindCode-4/code-10/tree/main/AECRNet

https://github.com/MindCode-4/code-11/tree/main/Duration-Informed-Attention-Network

DurIAN: Duration Informed Attention Network For Multimodal Synthesis

https://github.com/MindCode-4/code-13/tree/main/RawNet

RawNet: Fast End-to-End Neural Vocoder

https://github.com/MindCode-4/code-3/tree/main/data2vec

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

https://github.com/MindCode-4/code-3/tree/main/encodec

EnCodecMAE: Leveraging neural codecs for universal audio representation learning

https://github.com/MindCode-4/code-3/tree/main/fastspeech2_conformer

Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study

https://github.com/MindCode-4/code-5/tree/main/tvlt

TVLT: Textless Vision-Language Transformer

https://github.com/MindCode-4/code-5/tree/main/unispeech

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

https://github.com/MindCode-4/code-5/tree/main/unispeech_sat

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

https://github.com/MindCode-4/code-5/tree/main/univnet

UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation

https://github.com/MindCode-4/code-5/tree/main/wav2vec2_conformer

A comparative analysis between Conformer-Transducer, Whisper, and wav2vec2 for improving the child speech recognition

https://github.com/MindCode-4/code-5/tree/main/wavlm

WavLM model ensemble for audio deepfake detection

https://github.com/MindCode-4/code-5/tree/main/whisper

WhisperNER: Unified Open Named Entity and Speech Recognition

https://github.com/MindCode-4/code-5/tree/main/xlm_roberta

Unsupervised Cross-lingual Representation Learning for Speech Recognition

https://github.com/MindCode-4/code-6/tree/main/Duration-Informed-Attention-Network

DurIAN: Duration Informed Attention Network For Multimodal Synthesis

https://github.com/MindCode-4/code-9/tree/main/stochastic-attention-head-removal-a-simple

Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models

https://github.com/MindSpore-paper-code-2/code3/tree/main/Twins

Twin Regularization for online speech recognition

https://github.com/MindSpore-paper-code-2/code3/tree/main/swenet

WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit

https://github.com/MindSpore-paper-code-2/code399/tree/main/Bert_thor

HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units

https://github.com/MindSpore-paper-code-2/code399/tree/main/jasper

Jasper: An End-to-End Convolutional Neural Acoustic Model

https://github.com/MindSpore-paper-code-2/code399/tree/main/wavenet

Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram

https://github.com/MindSpore-paper-code-2/code400/tree/main/DeepSpeech2

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

https://github.com/MindSpore-paper-code-2/code400/tree/main/LPCNet

Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet

https://github.com/MindSpore-paper-code-2/code400/tree/main/Tacotron2

Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

https://github.com/MindSpore-paper-code-3/code2/tree/main/convnext

ConvNeXt Based Neural Network for Audio Anti-Spoofing

https://github.com/MindSpore-paper-code-3/code2/tree/main/crnn_seq2seq_ocr

The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS

https://github.com/MindSpore-paper-code-3/code9/tree/main/speech_transformer

A Simplified Fully Quantized Transformer for End-to-end Speech Recognition

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