English
Related papers

Related papers: MiniMind-O Technical Report: An Open Small-Scale S…

200 papers

Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data…

Computation and Language · Computer Science 2025-02-27 Zhenyan Lu , Xiang Li , Dongqi Cai , Rongjie Yi , Fangming Liu , Xiwen Zhang , Nicholas D. Lane , Mengwei Xu

Large Language Models (LLMs) have shown remarkable capabilities for complex tasks, yet adaptation in medical domain, specifically mental health, poses specific challenges. Mental health is a rising concern globally with LLMs having large…

Multimodal Large Languages models have been progressing from uni-modal understanding toward unifying visual, audio and language modalities, collectively termed omni models. However, the correlation between uni-modal and omni-modal remains…

Computation and Language · Computer Science 2025-10-31 Chen Chen , ZeYang Hu , Fengjiao Chen , Liya Ma , Jiaxing Liu , Xiaoyu Li , Ziwen Wang , Xuezhi Cao , Xunliang Cai

We propose a framework that enables neural models to "think while listening" to everyday sounds, thereby enhancing audio classification performance. Motivated by recent advances in the reasoning capabilities of large language models, we…

Sound · Computer Science 2025-09-25 Prateek Verma , Mert Pilanci

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech…

Computation and Language · Computer Science 2026-02-02 Yuxuan Lou , Ziming Wu , Yaochen Wang , Yong Liu , Yingxuan Ren , Fuming Lai , Shaobing Lian , Jie Tang , Yang You

In this paper, we evaluate feature extraction models for predicting speech quality. We also propose a model architecture to compare embeddings of supervised learning and self-supervised learning models with embeddings of speaker…

Current omni-modal benchmarks mainly evaluate models under settings where multiple modalities are provided simultaneously, while the ability to start from audio alone and actively search for cross-modal evidence remains underexplored. In…

Language assessment plays a crucial role in diagnosing and treating individuals with speech, language, and communication disorders caused by neurogenic conditions, whether developmental or acquired. However, current assessment methods are…

Computation and Language · Computer Science 2024-03-19 Charalambos Themistocleous

Neural scaling laws offer valuable insights for designing robust sequence processing architectures. While these laws have been extensively characterized in other modalities, their behavior in speech remains comparatively underexplored. In…

Computation and Language · Computer Science 2025-02-17 William Chen , Jinchuan Tian , Yifan Peng , Brian Yan , Chao-Han Huck Yang , Shinji Watanabe

The increasing complexity of large-scale language models has amplified concerns regarding their interpretability and reusability. While traditional embedding models like Word2Vec and GloVe offer scalability, they lack transparency and often…

Machine Learning · Computer Science 2025-05-23 Ahmed K. Kadhim , Lei Jiao , Rishad Shafik , Ole-Christoffer Granmo

Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech language models from performing instruction-based free-form…

Self-talk-an internal dialogue that can occur silently or be spoken aloud-plays a crucial role in emotional regulation, cognitive processing, and motivation, yet has remained largely invisible and unmeasurable in everyday life. In this…

Sound · Computer Science 2025-11-12 Euihyeok Lee , Seonghyeon Kim , SangHun Im , Heung-Seon Oh , Seungwoo Kang

Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or…

Audio and Speech Processing · Electrical Eng. & Systems 2019-09-04 Yan Deng , Lei He , Frank Soong

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

Multimedia · Computer Science 2026-03-09 Kin Wai Lau , Yasar Abbas Ur Rehman , Lai-Man Po , Pedro Porto Buarque de Gusmão

Underlying mechanisms of speech perception masked by background speakers, a common daily listening condition, are often investigated using various and lengthy psychophysical tests. The presence of a social agent, such as an interactive…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-18 Luke Meyer , Gloria Araiza-Illan , Laura Rachman , Etienne Gaudrain , Deniz Baskent

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Rowel Atienza

In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components using…

Machine Learning · Computer Science 2015-09-29 Georg Heigold , Ignacio Moreno , Samy Bengio , Noam Shazeer

We present Fox-1, a series of small language models (SLMs) consisting of Fox-1-1.6B and Fox-1-1.6B-Instruct-v0.1. These models are pre-trained on 3 trillion tokens of web-scraped document data and fine-tuned with 5 billion tokens of…

The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimodal inputs beyond text, such as speech and visual data,…

Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-17 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe