English
Related papers

Related papers: BoSS: Beyond-Semantic Speech

200 papers

Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS)…

Computation and Language · Computer Science 2026-04-13 Ilya Trofimenko , David Kocharyan , Aleksandr Zaitsev , Pavel Repnikov , Mark Levin , Nikita Shevtsov

Current state-of-the-art methods for automatic synthetic speech evaluation are based on MOS prediction neural models. Such MOS prediction models include MOSNet and LDNet that use spectral features as input, and SSL-MOS that relies on a…

Non-verbal signals in speech are encoded by prosody and carry information that ranges from conversation action to attitude and emotion. Despite its importance, the principles that govern prosodic structure are not yet adequately understood.…

Polysemanticity is pervasive in language models and remains a major challenge for interpretation and model behavioral control. Leveraging sparse autoencoders (SAEs), we map the polysemantic topology of two small models (Pythia-70M and…

Artificial Intelligence · Computer Science 2026-03-19 Bofan Gong , Shiyang Lai , James Evans , Dawn Song

Many dialogue systems (DSs) lack characteristics humans have, such as emotion perception, factuality, and informativeness. Enhancing DSs with knowledge alleviates this problem, but, as many ways of doing so exist, keeping track of all…

Computation and Language · Computer Science 2022-12-21 Sagi Shaier , Lawrence Hunter , Katharina Kann

Audio tokenizers are fundamental to unifying audio understanding and generation. Understanding requires high-level semantics, while generation demands semantic and acoustic details. Existing unified tokenizers jointly encode both in…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-28 Zhisheng Zhang , Xiang Li , Yixuan Zhou , Jing Peng , Guoyang Zeng , Zhiyong Wu

Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate…

Human-Computer Interaction · Computer Science 2025-10-13 Jijie Zhou , Yuhan Hu

Empathetic speech dialogue requires not only understanding linguistic content but also perceiving rich paralinguistic information such as prosody, tone, and emotional intensity for affective understandings. Existing speech-to-speech large…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Zhuoyue Gao , Xiaohui Wang , Xiaocui Yang , Wen Zhang , Daling Wang , Shi Feng , Yifei Zhang

Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-17 Siyang Wang , Éva Székely

Large language models (LLMs) have started to play a vital role in modelling speech and text. To explore the best use of context and multiple systems' outputs for post-ASR speech emotion prediction, we study LLM prompting on a recent task…

Computation and Language · Computer Science 2024-10-07 Pavel Stepachev , Pinzhen Chen , Barry Haddow

Semantic communication, regarded as the breakthrough beyond the Shannon paradigm, aims at the successful transmission of semantic information conveyed by the source rather than the accurate reception of each single symbol or bit regardless…

Information Theory · Computer Science 2022-06-28 Zhijin Qin , Xiaoming Tao , Jianhua Lu , Wen Tong , Geoffrey Ye Li

Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech…

Computation and Language · Computer Science 2025-04-11 Lakshmipathi Balaji , Karan Singla

End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…

Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require…

Computation and Language · Computer Science 2022-10-25 Sanchit Gandhi , Patrick von Platen , Alexander M. Rush

Despite being trained exclusively on speech data, speech foundation models (SFMs) like Whisper have shown impressive performance in non-speech tasks such as audio classification. This is partly because speech shares some common traits with…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-17 Orchid Chetia Phukan , Swarup Ranjan Behera , Girish , Mohd Mujtaba Akhtar , Arun Balaji Buduru , Rajesh Sharma

Despite the close relationship between speech perception and production, research in automatic speech recognition (ASR) and text-to-speech synthesis (TTS) has progressed more or less independently without exerting much mutual influence on…

Computation and Language · Computer Science 2017-07-18 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both generate and understand audio. However, preserving key…

Self-supervised language models are very effective at predicting high-level cortical responses during language comprehension. However, the best current models of lower-level auditory processing in the human brain rely on either…

Computation and Language · Computer Science 2022-05-31 Aditya R. Vaidya , Shailee Jain , Alexander G. Huth

Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly model the temporal dimension of memory in two…

Artificial Intelligence · Computer Science 2026-01-13 Miao Su , Yucan Guo , Zhongni Hou , Long Bai , Zixuan Li , Yufei Zhang , Guojun Yin , Wei Lin , Xiaolong Jin , Jiafeng Guo , Xueqi Cheng

Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…

Computation and Language · Computer Science 2022-02-28 Hemant Yadav , Sunayana Sitaram