conftrace_
← Techniques
Deep Learning › Techniques ›

Pretraining

2,483 papers

Papers per year

1
5
219
374
'10
'15
'20
'25

Papers

Forty Years of Speech and Language Processing: From Bayes Decision Rule to Deep Learning INTERSPEECH 2021
SUPERB: Speech Processing Universal PERformance Benchmark INTERSPEECH 2021
Pre-Training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning INTERSPEECH 2021
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion INTERSPEECH 2021
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling INTERSPEECH 2021
HMM-Free Encoder Pre-Training for Streaming RNN Transducer INTERSPEECH 2021
Using Large Self-Supervised Models for Low-Resource Speech Recognition INTERSPEECH 2021
Speech Denoising with Auditory Models INTERSPEECH 2021
LiRA: Learning Visual Speech Representations from Audio Through Self-Supervision INTERSPEECH 2021
Phrase Break Prediction with Bidirectional Encoder Representations in Japanese Text-to-Speech Synthesis INTERSPEECH 2021
Phoneme Duration Modeling Using Speech Rhythm-Based Speaker Embeddings for Multi-Speaker Speech Synthesis INTERSPEECH 2021
Language Recognition Based on Unsupervised Pretrained Models INTERSPEECH 2021
N-MTTL SI Model: Non-Intrusive Multi-Task Transfer Learning-Based Speech Intelligibility Prediction Model with Scenery Classification INTERSPEECH 2021
Emotion Recognition from Speech Using wav2vec 2.0 Embeddings INTERSPEECH 2021
Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone INTERSPEECH 2021
WavBERT: Exploiting Semantic and Non-Semantic Speech Using Wav2vec and BERT for Dementia Detection INTERSPEECH 2021
A Hands-On Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation INTERSPEECH 2021
Transformer Based End-to-End Mispronunciation Detection and Diagnosis INTERSPEECH 2021
An Improved Wav2Vec 2.0 Pre-Training Approach Using Enhanced Local Dependency Modeling for Speech Recognition INTERSPEECH 2021
Adaptive Text to Speech for Spontaneous Style INTERSPEECH 2021
Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-Trained DNN-HMM-Based Acoustic-Phonetic Model INTERSPEECH 2021
Speak or Chat with Me: End-to-End Spoken Language Understanding System with Flexible Inputs INTERSPEECH 2021
Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning MIDL 2021
A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks NAACL 2021
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code NAACL 2021