English
Related papers

Related papers: Baichuan-Audio: A Unified Framework for End-to-End…

200 papers

Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the…

Sound · Computer Science 2024-12-18 Kai Qiu , Xiang Li , Hao Chen , Jie Sun , Jinglu Wang , Zhe Lin , Marios Savvides , Bhiksha Raj

The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language…

Computation and Language · Computer Science 2025-10-10 Heyang Liu , Yuhao Wang , Ziyang Cheng , Ronghua Wu , Qunshan Gu , Yanfeng Wang , Yu Wang

This paper introduces the integration of language-specific bi-directional context into a speech large language model (SLLM) to improve multilingual continuous conversational automatic speech recognition (ASR). We propose a character-level…

Computation and Language · Computer Science 2025-07-08 Yizhou Peng , Hexin Liu , Eng Siong Chng

Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important issue associated with such approaches is that the intermediate…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-11 Jin Li , Rongfeng Su , Xurong Xie , Nan Yan , Lan Wang

Large language models (LLMs) have demonstrated strong capabilities in language understanding, generation, and reasoning, yet their potential in finance remains underexplored due to the complexity and specialization of financial knowledge.…

Computation and Language · Computer Science 2025-01-03 Hanyu Zhang , Boyu Qiu , Yuhao Feng , Shuqi Li , Qian Ma , Xiyuan Zhang , Qiang Ju , Dong Yan , Jian Xie

End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of…

Computation and Language · Computer Science 2022-02-17 Yotaro Kubo , Shigeki Karita , Michiel Bacchiani

The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning…

Sound · Computer Science 2024-06-17 Dongchao Yang , Haohan Guo , Yuanyuan Wang , Rongjie Huang , Xiang Li , Xu Tan , Xixin Wu , Helen Meng

The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training. However, this is typically not in the context of long audio recordings wherein the text being queried does not appear…

Computation and Language · Computer Science 2023-10-11 Piyush Singh Pasi , Karthikeya Battepati , Preethi Jyothi , Ganesh Ramakrishnan , Tanmay Mahapatra , Manoj Singh

The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…

Sound · Computer Science 2020-11-19 Yuxiang Kong , Jian Wu , Quandong Wang , Peng Gao , Weiji Zhuang , Yujun Wang , Lei Xie

End-to-end Speech-to-text Translation (E2E-ST), which directly translates source language speech to target language text, is widely useful in practice, but traditional cascaded approaches (ASR+MT) often suffer from error propagation in the…

Computation and Language · Computer Science 2021-02-10 Junkun Chen , Mingbo Ma , Renjie Zheng , Liang Huang

We present EmbodiedHead, a speech-driven talking-head framework that equips LLMs with real-time visual avatars for conversation. A practical embodied avatar must achieve real-time generation, unified listening-speaking behavior, and high…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yu Zhang , Kaiyuan Shen , Yang Li

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…

Sound · Computer Science 2026-05-15 Ryo Magoshi , Takashi Maekaku , Yusuke Shinohara

We present CALM, a joint Contextual Acoustic-Linguistic Modeling framework for multi-speaker automatic speech recognition (ASR). In personalized AI scenarios, the joint availability of acoustic and linguistic cues naturally motivates the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-14 Muhammad Shakeel , Yosuke Fukumoto , Chikara Maeda , Chyi-Jiunn Lin , Shinji Watanabe

Recently, representation learning for text and speech has successfully improved many language related tasks. However, all existing methods suffer from two limitations: (a) they only learn from one input modality, while a unified…

Computation and Language · Computer Science 2021-09-15 Renjie Zheng , Junkun Chen , Mingbo Ma , Liang Huang

Auditory foundation models, including auditory large language models (LLMs), process all sound inputs equally, independent of listener perception. However, human auditory perception is inherently selective: listeners focus on specific…

End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…

Computation and Language · Computer Science 2018-03-06 Zhehuai Chen , Qi Liu , Hao Li , Kai Yu

Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data…

In the era of large language models (LLMs) and artificial general intelligence (AGI), computer audition must evolve beyond traditional paradigms to fully leverage the capabilities of foundation models, towards more comprehensive…

Recent advances in the audio language modeling (ALM) domain tackle audio understanding and text-to-audio generation as separate tasks. Very few studies attempt to unify these tasks -- an essential step toward advanced multimodal reasoning.…

Voice Assistants such as Alexa, Siri, and Google Assistant typically use a two-stage Spoken Language Understanding pipeline; first, an Automatic Speech Recognition (ASR) component to process customer speech and generate text transcriptions,…

Computation and Language · Computer Science 2020-12-17 Subendhu Rongali , Beiye Liu , Liwei Cai , Konstantine Arkoudas , Chengwei Su , Wael Hamza