11 papers
DRAMA-Eval: A Benchmark for Context-Aware, Multi-Turn, Multi-Speaker Speech Generation
Jingbin Hu, Zihang Yang, Xiaoge Peng +21
Recent advances in speech generation are shifting toward context-aware, multi-turn, and multi-speaker synthesis. While these capabilities are in high demand for applications such a…
From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS
Kangxiang Xia, Xinfa Zhu, HangRui Hu +8
Multi-speaker dialogue TTS requires natural speech generation, consistent speaker identity, coherent cross-turn transitions, and fine-grained control of expressive attributes such…
Interactive TTS: Dynamic Speaking Style Adaptation for Expressive Speech Synthesis
Wenjie Tian, Kangxiang Xia, Jingbin Hu +7
Dynamic speaking style adaptation in multi-turn multimodal interaction remains a major challenge for text-to-speech (TTS) systems. Existing context-aware TTS (CTTS) methods typical…
Bridging Data, Reasoning, and Alignment: A Unified Framework for Context-Aware Instruction-Following TTS
Jingbin Hu, Luyu Wang, Wenjie Tian +7
The ISCSLP 2026 CoT-TTS Challenge requires TTS systems to generate Chain-of-Thought (CoT) reasoning from dialogue history before synthesizing contextually appropriate speech. While…
Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model
Kangxiang Xia, Bingshen Mu, Xian Shi +2
Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions a…
VoiceSculptor: Your Voice, Designed By You
Jingbin Hu, Huakang Chen, Linhan Ma +19
Despite rapid progress in text-to-speech (TTS), open-source systems still lack truly instruction-following, fine-grained control over core speech attributes (e.g., pitch, speaking…
OSUM-EChat: Enhancing End-to-End Empathetic Spoken Chatbot via Understanding-Driven Spoken Dialogue
Xuelong Geng, Qijie Shao, Hongfei Xue +20
Empathy is crucial in enabling natural interactions within spoken dialogue systems, allowing machines to recognize and respond appropriately to paralinguistic cues such as age, gen…
MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
Kangxiang Xia, Xinfa Zhu, Jixun Yao +1
In recent years, text-to-speech (TTS) has seen impressive advancements through large-scale language models, achieving human-level speech quality. Integrating human feedback has pro…
KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction
Kangxiang Xia, Xinfa Zhu, Jixun Yao +3
We introduce KALL-E, a novel autoregressive (AR) language model for text-to-speech (TTS) synthesis that operates by predicting the next distribution of continuous speech frames. Un…
The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings
Kangxiang Xia, Dake Guo, Jixun Yao +9
The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge aims to benchmark and advance zero-shot spontaneous style voice cloning, particularly focusing on generating spontaneou…
The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge
Dake Guo, Jixun Yao, Xinfa Zhu +6
This paper presents the NPU-HWC system submitted to the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC). Our system consists of two modules: a spee…