13 citations · 45 across the 18 of their papers we have counts for
19 papers
FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
Shoutao Guo, Shaolei Zhang, Qingkai Fang +3
The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understa…
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
Zhengrui Ma, Yang Feng, Chenze Shao +3
We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregres…
Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation
Shoutao Guo, Shaolei Zhang, Zhengrui Ma +1
Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneo…
Overcoming Non-monotonicity in Transducer-based Streaming Generation
Zhengrui Ma, Yang Feng, Min Zhang
Streaming generation models are utilized across fields, with the Transducer architecture being popular in industrial applications. However, its input-synchronous decoding mechanism…
LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Qingkai Fang, Shoutao Guo, Yan Zhou +3
Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interac…
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
Shoutao Guo, Shaolei Zhang, Zhengrui Ma +2
Simultaneous Machine Translation (SiMT) generates target translations while reading the source sentence. It relies on a policy to determine the optimal timing for reading sentences…
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Qingkai Fang, Zhengrui Ma, Yan Zhou +2
Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but it often faces the challenge of slow decoding due to the considerable length of speech s…
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
Qingkai Fang, Shaolei Zhang, Zhengrui Ma +2
Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end…
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Shaolei Zhang, Qingkai Fang, Shoutao Guo +3
Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real…
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation
Zhengrui Ma, Qingkai Fang, Shaolei Zhang +3
Simultaneous translation models play a crucial role in facilitating communication. However, existing research primarily focuses on text-to-text or speech-to-text models, necessitat…
SiLLM: Large Language Models for Simultaneous Machine Translation
Shoutao Guo, Shaolei Zhang, Zhengrui Ma +2
Simultaneous Machine Translation (SiMT) generates translations while reading the source sentence, necessitating a policy to determine the optimal timing for reading and generating…
Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
Shangtong Gui, Chenze Shao, Zhengrui Ma +3
Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and…
Beyond MLE: Convex Learning for Text Generation
Chenze Shao, Zhengrui Ma, Min Zhang +1
Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of tex…
Non-autoregressive Streaming Transformer for Simultaneous Translation
Zhengrui Ma, Shaolei Zhang, Shoutao Guo +3
Simultaneous machine translation (SiMT) models are trained to strike a balance between latency and translation quality. However, training these models to achieve high quality while…
BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang +8
Large language models (LLMs) have demonstrated remarkable prowess in language understanding and generation. Advancing from foundation LLMs to instructionfollowing LLMs, instruction…
Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
Zhengrui Ma, Chenze Shao, Shangtong Gui +2
Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed ac…
Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Chenze Shao, Zhengrui Ma, Yang Feng
Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA…
Smoothed Multi-View Subspace Clustering
Peng Chen, Liang Liu, Zhengrui Ma +1
In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views. However, multi-view…
Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
Zhengrui Ma, Zhao Kang, Guangchun Luo +1
Finding a suitable data representation for a specific task has been shown to be crucial in many applications. The success of subspace clustering depends on the assumption that the…