Papers with Code 아카이브

Automatic Speech Recognition (ASR)

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/idiap/rnv

공식 코드

Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech

https://github.com/idiap/slu_representations

공식 코드

Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasks

https://github.com/idiap/ssl-human-animal

공식 코드

Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing

https://github.com/idiap/w2v2-air-traffic

공식 코드

How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications

https://github.com/iiscleap/joint_fdlp_envelope_dereverberation_e2e_asr

공식 코드

End-to-End Speech Recognition With Joint Dereverberation Of Sub-Band Autoregressive Envelopes

https://github.com/indonlp/nusa-crowd

공식 코드

NusaCrowd: Open Source Initiative for Indonesian NLP Resources

https://github.com/jairsan/segmentation-free_streaming_machine_translation

공식 코드

Segmentation-Free Streaming Machine Translation

https://github.com/jb1999/eesen

공식 코드

Improving LSTM-CTC based ASR performance in domains with limited training data

https://github.com/jctian98/e2e_lfmmi

공식 코드

Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMI

https://github.com/jeromeni/wholeword-uasr-jstti

공식 코드

Towards Unsupervised Speech Recognition Without Pronunciation Models

https://github.com/jethrowangsir/cada-gan

공식 코드

Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition

https://github.com/jhauret/vibravox

공식 코드

Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors

https://github.com/jianboma/low_latency_attention_module

공식 코드

A low latency attention module for streaming self-supervised speech representation learning

https://github.com/jindongwang/transferlearning/tree/master/code/ASR/CMatch

공식 코드

Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching

https://github.com/jjdean321/espnet_conformer_lhuc

공식 코드

Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems

https://github.com/joonaskalda/pixit

공식 코드

PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings

https://github.com/joungheekim/k-wav2vec

공식 코드

K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables

https://github.com/jsalsman/featex

공식 코드

Spoken English Intelligibility Remediation with PocketSphinx Alignment and Feature Extraction Improves Substantially over the State of the Art

https://github.com/jsalt2022codeswitchingasr/generating-code-switched-audio

공식 코드

Speech collage: code-switched audio generation by collaging monolingual corpora

https://github.com/juice500ml/dysarthria-mtl

공식 코드

Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with Multi-task Learning

https://github.com/juice500ml/xlm_to_xlsr

공식 코드

Distilling a Pretrained Language Model to a Multilingual ASR Model

https://github.com/jxzhanggg/DistillAV

공식 코드

Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models

https://github.com/k2-fsa/icefall

공식 코드

Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation

https://github.com/k2-fsa/k2

공식 코드

Delay-penalized transducer for low-latency streaming ASR

https://github.com/kaldi-asr/kaldi

공식 코드

A Parallelizable Lattice Rescoring Strategy with Neural Language Models

https://github.com/kaldi-asr/kaldi/tree/master/egs/tedlium/s5_r3

공식 코드

TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation

https://github.com/kathania/Interspeech-2020-Non-native-children-ASR

공식 코드

Data augmentation using prosody and false starts to recognize non-native children's speech

https://github.com/kehanlu/mandarin-wav2vec2

공식 코드

A context-aware knowledge transferring strategy for CTC-based ASR

https://github.com/khfs/DuplexMamba

공식 코드

DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities

https://github.com/knowledgetechnologyuhh/meld-fair

공식 코드

Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge

https://github.com/koenecke/auditing_asr_aphasia

공식 코드

Addressing Pitfalls in Auditing Practices of Automatic Speech Recognition Technologies: A Case Study of People with Aphasia

https://github.com/kssteven418/squeezeformer

공식 코드

Squeezeformer: An Efficient Transformer for Automatic Speech Recognition

https://github.com/leduckhai/multimed

공식 코드

Sentiment Reasoning for Healthcare

https://github.com/leduckhai/sentiment-reasoning

공식 코드

Sentiment Reasoning for Healthcare

https://github.com/leduckhai/wav2graph

공식 코드

wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech

https://github.com/linguisticanomalies/paradox-asr

공식 코드

The Far Side of Failure: Investigating the Impact of Speech Recognition Errors on Subsequent Dementia Classification

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