Papers by Dongchao Yang

6 papers
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach: They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome: The proposed model performs better on 200K hours of 6-language data for voice generation applications.
Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach: They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome: The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.
Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Speech Large Language Models (SpeechLLMs) have emerged as dominant speech processing approaches.
Approach: They compare self-supervised learning-based discrete and continuous features . they compare performance across six spoken language understanding-related tasks .
Outcome: The proposed models outperform discrete tokens and continuous features in six spoken language understanding-related tasks.
ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors (2025.acl-long)

Copied to clipboard

Challenge: Existing multilingual audio-text retrieval schemes suffer from inconsistencies for instance similarity matching across languages.
Approach: They propose a multilingual audio-text retrieval scheme that mitigates the impact of data distribution error on recall and consistency.
Outcome: The proposed scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English.
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in speech large language models exhibit suboptimal performance in adhering to speech instructions.
Approach: They propose a method to pre-train large-scale unsupervised speech-text sequences . they use text-to-speech conversion to generate textual continuations corresponding to provided speech segments .
Outcome: The proposed model achieves superior or competitive results across diverse speech processing tasks.
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for speech generation rely on subjective, expensive judgments . Existing models only cover a narrow set of scenarios and only provide limited coverage .
Approach: They propose a unified speech reward model that can support multi-dimensional, interpretable reward signals with reliable reasoning.
Outcome: The proposed model can support multi-dimensional, interpretable reward signals with reliable reasoning.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations