English
Related papers

Related papers: HarmoniFuse: A Component-Selective and Prompt-Adap…

200 papers

Continuous autoregressive speech synthesis has recently emerged as a promising direction for zero-shot text-to-speech (TTS). However, existing methods still suffer from a fundamental mismatch between semantic-prosodic modeling and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-19 Huimeng Wang , Hui Lu , Jiajun Deng , Haoning Xu , Youjun Chen , Xueyuan Chen , Zhaoqing Li , Shuhai Peng , Shiyin Kang , Xunying Liu

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Computation and Language · Computer Science 2024-10-25 Hawau Olamide Toyin , Hao Li , Hanan Aldarmaki

Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. It is thus possible to use a single transducer model to perform both tasks. In real-world applications, such joint ASR…

Computation and Language · Computer Science 2023-10-23 Peidong Wang , Eric Sun , Jian Xue , Yu Wu , Long Zhou , Yashesh Gaur , Shujie Liu , Jinyu Li

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Computation and Language · Computer Science 2024-12-03 Aohan Zeng , Zhengxiao Du , Mingdao Liu , Lei Zhang , Shengmin Jiang , Yuxiao Dong , Jie Tang

The combination of Large Language Models (LLM) and Automatic Speech Recognition (ASR), when deployed on edge devices (called edge ASR-LLM), can serve as a powerful personalized assistant to enable audio-based interaction for users. Compared…

Sentiment analysis models exhibit complementary strengths, yet existing approaches lack a unified framework for effective integration. We present SentiFuse, a flexible and model-agnostic framework that integrates heterogeneous sentiment…

Computation and Language · Computer Science 2026-02-03 Hieu Minh Duong , Rupa Ghosh , Cong Hoan Nguyen , Eugene Levin , Todd Gary , Long Nguyen

Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is…

Computation and Language · Computer Science 2024-06-14 Amit Meghanani , Thomas Hain

We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this…

Computation and Language · Computer Science 2024-02-08 Mingqiu Wang , Izhak Shafran , Hagen Soltau , Wei Han , Yuan Cao , Dian Yu , Laurent El Shafey

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Computation and Language · Computer Science 2021-01-28 Jiahui Yu , Wei Han , Anmol Gulati , Chung-Cheng Chiu , Bo Li , Tara N. Sainath , Yonghui Wu , Ruoming Pang

Speech Foundation Models have gained significant attention recently. Prior works have shown that the fusion of representations from multiple layers of the same model or the fusion of multiple models can improve performance on downstream…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-12 Yi-Jen Shih , David Harwath

LLM-based automatic speech recognition (ASR), a well-established approach, connects speech foundation models to large language models (LLMs) through a speech-to-LLM projector, yielding promising results. A common design choice in these…

This paper describes SHNU multilingual conversational speech recognition system (SHNU-mASR, team name-"maybe"), submitted to Track 1 of the INTERSPEECH 2025 MLC-SLM Challenge. Our system integrates a parallel-speech-encoder architecture…

Computation and Language · Computer Science 2025-07-09 Yuxiang Mei , Yuang Zheng , Dongxing Xu , Yanhua Long

Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-28 Umberto Cappellazzo , Xubo Liu , Pingchuan Ma , Stavros Petridis , Maja Pantic

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

Computation and Language · Computer Science 2025-10-23 Ju-Chieh Chou , Jiawei Zhou , Karen Livescu

Speech summarization, which generates a text summary from speech, can be achieved by combining automatic speech recognition (ASR) and text summarization (TS). With this cascade approach, we can exploit state-of-the-art models and large…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-17 Takatomo Kano , Atsunori Ogawa , Marc Delcroix , Shinji Watanabe

Noise-robust automatic speech recognition (ASR) has been commonly addressed by applying speech enhancement (SE) at the waveform level before recognition. However, speech-level enhancement does not always translate into consistent…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-09 Da-Hee Yang , Joon-Hyuk Chang

This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method…

Computation and Language · Computer Science 2025-08-12 Zeyu Yang , Lai Wei , Roman Koshkin , Xi Chen , Satoshi Nakamura

Accents, as variations from standard pronunciation, pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling…

Sound · Computer Science 2023-11-20 Qijie Shao , Pengcheng Guo , Jinghao Yan , Pengfei Hu , Lei Xie

Automatic speech recognition (ASR) is critical for language accessibility, yet low-resource Cantonese remains challenging due to limited annotated data, six lexical tones, tone sandhi, and accent variation. Existing ASR models, such as…

Computation and Language · Computer Science 2025-11-07 Dazhong Chen , Yi-Cheng Lin , Yuchen Huang , Ziwei Gong , Di Jiang , Zeying Xie , Yi R. , Fung

How to make human-interpreter-like read/write decisions for simultaneous speech translation (SimulST) systems? Current state-of-the-art systems formulate SimulST as a multi-turn dialogue task, requiring specialized interleaved training data…

Computation and Language · Computer Science 2026-02-02 Haotian Tan , Hiroki Ouchi , Sakriani Sakti