collaborators

6 papers

cs.SD2026

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

Lianbo Liu, Shiao Zhu, Kai Washizaki +10

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, howev…

cs.SD2026

Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization

Mengjie Zhao, Lianbo Liu, Yusuke Fujita +4

SpeechLLMs typically combine ASR-trained encoders with text-based LLM backbones, leading them to inherit written-style output patterns unsuitable for text-to-speech synthesis. This…

cs.CL2026

Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

Roman Koshkin, Jeon Haesung, Lianbo Liu +4

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hika…

cs.SD2026

Distilling LLM Semantic Priors into Encoder-Only Multi-Talker ASR with Talker-Count Routing

Hao Shi, Yusuke Fujita, Roman Koshkin +4

Large language models (LLMs) provide strong semantic priors that can improve multi-talker automatic speech recognition (MT-ASR), but using an LLM as an autoregressive decoder is co…

cs.CL2025

SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation

Zeyu Yang, Lai Wei, Roman Koshkin +2

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, ver…

cs.CL2025

MaRGen: Multi-Agent LLM Approach for Self-Directed Market Research and Analysis

Roman Koshkin, Pengyu Dai, Nozomi Fujikawa +2

We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employ…