1 citations · 2 across the 12 of their papers we have counts for
16 papers
DisCo-Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec
Tao Li, Wenshuo Ge, Zhichao Wang +6
Codec-based language models (LMs) have revolutionized text-to-speech (TTS). However, standard codecs entangle timbre and prosody, which hinders independent control in continuation-…
Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation
Runyan Yang, Yuke Si, Yingying Gao +3
While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well…
HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modeling
Yuke Si, Runyan Yang, Yingying Gao +3
Recent advances in large language models have facilitated the development of unified speech language models (SLMs) capable of supporting multiple speech tasks within a shared archi…
DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners
Xiaoxue Luo, Jinwei Huang, Runyan Yang +4
Universal audio codecs learn entangled representations across audio types, whereas some specific codecs offer decoupled representations but are limited to speech. Real-world audio,…
GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model
Yingying Gao, Shilei Zhang, Chao Deng +1
Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream t…
PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models
Runyan Yang, Huibao Yang, Xiqing Zhang +6
Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of d…
Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
Yanan Chen, Zihao Cui, Yingying Gao +3
The expectation to deploy a universal neural network for speech enhancement, with the aim of improving noise robustness across diverse speech processing tasks, faces challenges due…
Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search
Yingying Gao, Shilei Zhang, Zihao Cui +2
Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our…
GenDistiller: Distilling Pre-trained Language Models based on Generative Models
Yingying Gao, Shilei Zhang, Zihao Cui +3
Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks…
VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting
Ao Zhang, He Wang, Pengcheng Guo +5
The performance of the keyword spotting (KWS) system based on audio modality, commonly measured in false alarms and false rejects, degrades significantly under the far field and no…
Meta Auxiliary Learning for Low-resource Spoken Language Understanding
Yingying Gao, Junlan Feng, Chao Deng +1
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We…
A CTC Triggered Siamese Network with Spatial-Temporal Dropout for Speech Recognition
Yingying Gao, Junlan Feng, Tianrui Wang +2
Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations fo…
Multiple Confidence Gates For Joint Training Of SE And ASR
Tianrui Wang, Weibin Zhu, Yingying Gao +2
Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory q…
Harmonic gated compensation network plus for ICASSP 2022 DNS CHALLENGE
Tianrui Wang, Weibin Zhu, Yingying Gao +3
The harmonic structure of speech is resistant to noise, but the harmonics may still be partially masked by noise. Therefore, we previously proposed a harmonic gated compensation ne…
HGCN: Harmonic gated compensation network for speech enhancement
Tianrui Wang, Weibin Zhu, Yingying Gao +2
Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement. However, it is hard for most mo…
Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
Xing Wang, Juan Zhao, Lin Zhu +5
Mobile network traffic forecasting is one of the key functions in daily network operation. A commercial mobile network is large, heterogeneous, complex and dynamic. These intrinsic…