Search Results for author:
Found 14 papers, 3 papers with code
A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data
We introduce DAS (Domain Adaptation with Synthetic data), a novel domain adaptation framework for pre-trained ASR model, designed to efficiently adapt to various language-defined domains without requiring any real data.
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases.
Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before.
LLaMA based Punctuation Restoration With Forward Pass Only Decoding
This paper introduces two advancements in the field of Large Language Model Annotation with a focus on punctuation restoration tasks.
FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation
Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted.
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Results demonstrate that our TODM Supernet either matches or surpasses the performance of manually tuned models by up to a relative of 3% better in word error rate (WER), while efficiently keeping the cost of training many models at a small constant.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
LiCo-Net: Linearized Convolution Network for Hardware-efficient Keyword Spotting
This paper proposes a hardware-efficient architecture, Linearized Convolution Network (LiCo-Net) for keyword spotting.
SCA: Streaming Cross-attention Alignment for Echo Cancellation
End-to-End deep learning has shown promising results for speech enhancement tasks, such as noise suppression, dereverberation, and speech separation.
U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.
WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Ranked #12 on
Speech Recognition
on AISHELL-1
Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization
Using knowledge distillation with trust regularization, we reduce the parameter size to a third of that of the previously published best model while maintaining the state-of-the-art perplexity result on Penn Treebank data.
Direct Object Recognition Without Line-of-Sight Using Optical Coherence
Visual object recognition under situations in which the direct line-of-sight is blocked, such as when it is occluded around the corner, is of practical importance in a wide range of applications.
End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model
In this paper, we propose to use a high rank projection layer to replace the projection matrix.
