Yusuke Shinohara

Yusuke Shinohara, Shinji Watanabe

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods, such as alignment-restricted training and FastEmit, have been studied to reduce the latency, latency reduction is often accompanied with a significant degradation in accuracy. We argue that this suboptimal performance might be caused because none of the prior methods explicitly model and reduce the latency. In this paper, we propose a new training method to explicitly model and reduce the latency of sequence transducer models. First, we define the expected latency at each diagonal line on the lattice, and show that its gradient can be computed efficiently within the forward-backward algorithm. Then we augment the transducer loss with this expected latency, so that an optimal trade-off between latency and accuracy is achieved. Experimental results on the WSJ dataset show that the proposed minimum latency training reduces the latency of causal Conformer-T from 220 ms to 27 ms within a WER degradation of 0.7%, and outperforms conventional alignment-restricted training (110 ms) and FastEmit (67 ms) methods.

Jinchuan Tian, Haoran Wang, Bo-Hao Su et al.

Current audio foundation models typically rely on rigid, task-specific supervision, addressing isolated factors of audio rather than the whole. In contrast, human intelligence processes audio holistically, seamlessly bridging physical signals with abstract cognitive concepts to execute complex tasks. Grounded in this philosophy, we introduce Bagpiper, an 8B audio foundation model that interprets physical audio via rich captions, i.e., comprehensive natural language descriptions that encapsulate the critical cognitive concepts inherent in the signal (e.g., transcription, audio events). By pre-training on a massive corpus of 600B tokens, the model establishes a robust bidirectional mapping between raw audio and this high-level conceptual space. During fine-tuning, Bagpiper adopts a caption-then-process workflow, simulating an intermediate cognitive reasoning step to solve diverse tasks without task-specific priors. Experimentally, Bagpiper outperforms Qwen-2.5-Omni on MMAU and AIRBench for audio understanding and surpasses CosyVoice3 and TangoFlux in generation quality, capable of synthesizing arbitrary compositions of speech, music, and sound effects. To the best of our knowledge, Bagpiper is among the first works that achieve unified understanding generation for general audio. Model, data, and code are available at Bagpiper Home Page.

Jinchuan Tian, William Chen, Yifan Peng et al. · nvidia

This paper presents Open Unified Speech Language Models (OpusLMs), a family of open foundational speech language models (SpeechLMs) up to 7B. Initialized from decoder-only text language models, the OpusLMs are continuously pre-trained on 213K hours of speech-text pairs and 292B text-only tokens. We demonstrate our OpusLMs achieve comparable (or even superior) performance with existing SpeechLMs in speech recognition, speech synthesis, and text-only capabilities. Technically, this paper articulates our SpeechLM designs on tokenization, multi-stream language models, and multi-stage training strategies. We experimentally demonstrate the importance of model size scaling and the effect of annealing data selection. The OpusLMs are all built from publicly available materials and are fully transparent models. We release our code, data, checkpoints, and training logs to facilitate open SpeechLM research

Ryo Magoshi, Takashi Maekaku, Yusuke Shinohara

LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only domain adaptation crucial. Existing methods typically rely on either fine-tuning the LLM alone or employing pseudo-audio prompts. The former neglects essential acoustic context, while the latter either suffers from limited scalability in data-scarce conditions, or yields inexpressive prompts by leveraging only textual features, ignoring audio modality. To address this, we propose an enhanced framework that explicitly models speech-text alignment. Our method efficiently generates highly expressive pseudo-audio prompts that bridges the modality gap, enabling effective target-domain adaptation. Experiments demonstrate that our approach outperforms existing text-only methods, improving both overall error rates and out-of-vocabulary coverage.

Takehiro Aoshima, Yusuke Shinohara, Byeongseon Park

Reward-based fine-tuning of video diffusion models is an effective approach to improve the quality of generated videos, as it can fine-tune models without requiring real-world video datasets. However, it can sometimes be limited to specific performances because conventional reward functions are mainly aimed at enhancing the quality across the whole generated video sequence, such as aesthetic appeal and overall consistency. Notably, the temporal consistency of the generated video often suffers when applying previous approaches to image-to-video (I2V) generation tasks. To address this limitation, we propose Video Consistency Distance (VCD), a novel metric designed to enhance temporal consistency, and fine-tune a model with the reward-based fine-tuning framework. To achieve coherent temporal consistency relative to a conditioning image, VCD is defined in the frequency space of video frame features to capture frame information effectively through frequency-domain analysis. Experimental results across multiple I2V datasets demonstrate that fine-tuning a video generation model with VCD significantly enhances temporal consistency without degrading other performance compared to the previous method.

Florian Boyer, Yusuke Shinohara, Takaaki Ishii et al.

In this study, we present recent developments of models trained with the RNN-T loss in ESPnet. It involves the use of various architectures such as recently proposed Conformer, multi-task learning with different auxiliary criteria and multiple decoding strategies, including our own proposition. Through experiments and benchmarks, we show that our proposed systems can be competitive against other state-of-art systems on well-known datasets such as LibriSpeech and AISHELL-1. Additionally, we demonstrate that these models are promising against other already implemented systems in ESPnet in regards to both performance and decoding speed, enabling the possibility to have powerful systems for a streaming task. With these additions, we hope to expand the usefulness of the ESPnet toolkit for the research community and also give tools for the ASR industry to deploy our systems in realistic and production environments.