中文
相关论文

相关论文: Speech ReaLLM -- Real-time Streaming Speech Recogn…

200 篇论文

Recent works have shown that prompting large language models with audio encodings can unlock speech recognition capabilities. However, existing techniques do not scale efficiently, especially while handling long form streaming audio inputs…

Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…

计算与语言 · 计算机科学 2025-08-08 Wenqian Cui , Dianzhi Yu , Xiaoqi Jiao , Ziqiao Meng , Guangyan Zhang , Qichao Wang , Yiwen Guo , Irwin King

Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promises to exploit paralinguistic information in the speech and to…

计算与语言 · 计算机科学 2026-05-15 Titouan Parcollet , Shucong Zhang , Xianrui Zheng , Rogier C. van Dalen

Decoder-only language models (LMs) have been successfully adopted for speech-processing tasks including automatic speech recognition (ASR). The LMs have ample expressiveness and perform efficiently. This efficiency is a suitable…

音频与语音处理 · 电气工程与系统科学 2024-08-02 Emiru Tsunoo , Hayato Futami , Yosuke Kashiwagi , Siddhant Arora , Shinji Watanabe

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

计算与语言 · 计算机科学 2025-09-08 Jaekwon Yoo , Kunal Chandiramani , Divya Tadimeti , Abenezer Girma , Chandra Dhir

In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…

音频与语音处理 · 电气工程与系统科学 2025-06-17 Jiajun He , Naoki Sawada , Koichi Miyazaki , Tomoki Toda

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Jeong Hun Yeo , Hyeongseop Rha , Se Jin Park , Yong Man Ro

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

声音 · 计算机科学 2020-07-02 Niko Moritz , Takaaki Hori , Jonathan Le Roux

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

计算与语言 · 计算机科学 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…

计算与语言 · 计算机科学 2025-05-27 Richard He Bai , Zijin Gu , Tatiana Likhomanenko , Navdeep Jaitly

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

计算与语言 · 计算机科学 2025-04-23 Keqi Deng , Wenxi Chen , Xie Chen , Philip C. Woodland

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training…

计算机视觉与模式识别 · 计算机科学 2025-04-23 Joya Chen , Ziyun Zeng , Yiqi Lin , Wei Li , Zejun Ma , Mike Zheng Shou

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In…

声音 · 计算机科学 2026-03-13 Yinfeng Xia , Jian Tang , Junfeng Hou , Gaopeng Xu , Haitao Yao

Recent research shows end-to-end ASR systems can recognize overlapped speech from multiple speakers. However, all published works have assumed no latency constraints during inference, which does not hold for most voice assistant…

音频与语音处理 · 电气工程与系统科学 2021-02-22 Ilya Sklyar , Anna Piunova , Yulan Liu

Despite extensions to speech inputs, effectively leveraging the rich knowledge and contextual understanding of large language models (LLMs) in automatic speech recognition (ASR) remains non-trivial, as the task primarily involves direct…

计算与语言 · 计算机科学 2026-04-02 Keqi Deng , Ruchao Fan , Bo Ren , Yiming Wang , Jinyu Li

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

声音 · 计算机科学 2026-01-27 Wenjie Tian , Bingshen Mu , Guobin Ma , Xuelong Geng , Zhixian Zhao , Lei Xie

In interactive automatic speech recognition (ASR) systems, low-latency requirements limit the amount of search space that can be explored during decoding, particularly in end-to-end neural ASR. In this paper, we present a novel streaming…

音频与语音处理 · 电气工程与系统科学 2024-01-29 Denis Filimonov , Prabhat Pandey , Ariya Rastrow , Ankur Gandhe , Andreas Stolcke

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

声音 · 计算机科学 2026-01-19 Bingshen Mu , Hexin Liu , Hongfei Xue , Kun Wei , Lei Xie

Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech processing, more…

计算与语言 · 计算机科学 2023-09-19 Cheng-I Jeff Lai , Zhiyun Lu , Liangliang Cao , Ruoming Pang
‹ 上一页 1 2 3 10 下一页 ›