9 papers
Factorized Delayed Streams Modeling for LLM-based Streaming ASR
Tatsunari Takagi, Kai Washizaki, Atsushi Kojima +3
Delayed Streams Modeling (DSM) enables LLM-based streaming automatic speech recognition (ASR) by aligning acoustic and text streams on a common timeline. DSM adds the padding token…
Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models
Tomoya Mizumoto, Yusuke Fujita, Hao Shi +3
Dialogue systems based on large language models (LLMs) have advanced significantly in recent years. However, dialectal variation remains a major challenge, particularly for systems…
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…
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…
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…
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…
Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognition
Hao Shi, Yusuke Fujita, Tomoya Mizumoto +3
Prompts are crucial for task definition and for improving the performance of large language models (LLM)-based systems. However, existing LLM-based multi-talker (MT) automatic spee…
AC/DC: LLM-based Audio Comprehension via Dialogue Continuation
Yusuke Fujita, Tomoya Mizumoto, Atsushi Kojima +2
We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating targe…
OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
Yui Sudo, Yusuke Fujita, Atsushi Kojima +2
Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SF…