research
∙
09/18/2023
HypR: A comprehensive study for ASR hypothesis revising with a reference corpus
With the development of deep learning, automatic speech recognition (ASR...
share
research
∙
05/18/2023
A Lexical-aware Non-autoregressive Transformer-based ASR Model
Non-autoregressive automatic speech recognition (ASR) has become a mains...
research
∙
10/12/2022
A context-aware knowledge transferring strategy for CTC-based ASR
Non-autoregressive automatic speech recognition (ASR) modeling has recei...
research
∙
08/01/2021
Versa: A Dataflow-Centric Multiprocessor with 36 Systolic ARM Cortex-M4F Cores and a Reconfigurable Crossbar-Memory Hierarchy in 28nm
We present Versa, an energy-efficient processor with 36 systolic ARM Cor...
research
∙
06/24/2021
A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021
In this paper, inspired by the successes of visionlanguage pre-trained m...
research
∙
04/10/2021
Non-autoregressive Transformer-based End-to-end ASR using BERT
Transformer-based models have led to a significant innovation in various...
research
∙
01/30/2021
Speech Recognition by Simply Fine-tuning BERT
We propose a simple method for automatic speech recognition (ASR) by fin...
research
∙
07/11/2020
Investigation of Sentiment Controllable Chatbot
Conventional seq2seq chatbot models attempt only to find sentences with ...
research
∙
05/25/2020
An Audio-enriched BERT-based Framework for Spoken Multiple-choice Question Answering
In a spoken multiple-choice question answering (SMCQA) task, given a pas...
research
∙
10/31/2019
A neural document language modeling framework for spoken document retrieval
Recent developments in deep learning have led to a significant innovatio...
research
∙
04/08/2019
Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models
Producing a large annotated speech corpus for training ASR systems remai...
research
∙
04/07/2018
Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis
Conventional seq2seq chatbot models only try to find the sentences with ...
research
∙
04/01/2018
Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings
Unsupervised discovery of acoustic tokens from audio corpora without ann...
research
∙
11/22/2016
Learning to Distill: The Essence Vector Modeling Framework
In the context of natural language processing, representation learning h...
research
∙
07/22/2016
Novel Word Embedding and Translation-based Language Modeling for Extractive Speech Summarization
Word embedding methods revolve around learning continuous distributed ve...
research
∙
01/20/2016
Improved Spoken Document Summarization with Coverage Modeling Techniques
Extractive summarization aims at selecting a set of indicative sentences...
research
∙
06/14/2015