English
Related papers

Related papers: Whisfusion: Parallel ASR Decoding via a Diffusion …

200 papers

Autoregressive (AR) language models generate text one token at a time, which limits their inference speed. Diffusion-based language models offer a promising alternative, as they can decode multiple tokens in parallel. However, we identify a…

Computation and Language · Computer Science 2025-10-27 Yeongbin Seo , Dongha Lee , Jaehyung Kim , Jinyoung Yeo

Large transformer-based models have significant potential for speech transcription and translation. Their self-attention mechanisms and parallel processing enable them to capture complex patterns and dependencies in audio sequences.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Yael Segal-Feldman , Aviv Shamsian , Aviv Navon , Gill Hetz , Joseph Keshet

Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important…

Computation and Language · Computer Science 2025-04-01 Michael McGuire

Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas…

Sound · Computer Science 2025-04-23 Rongxiang Wang , Zhiming Xu , Felix Xiaozhu Lin

Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion…

Sound · Computer Science 2024-07-04 Jinming Chen , Jingyi Fang , Yuanzhong Zheng , Yaoxuan Wang , Haojun Fei

This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…

Computation and Language · Computer Science 2021-04-20 Takaaki Hori , Niko Moritz , Chiori Hori , Jonathan Le Roux

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…

Computation and Language · Computer Science 2026-03-06 Jia-Nan Li , Jian Guan , Wei Wu , Chongxuan Li

As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to…

Sound · Computer Science 2025-05-06 Haoyu Wang , Guoqiang Hu , Guodong Lin , Wei-Qiang Zhang , Jian Li

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Computation and Language · Computer Science 2025-12-02 Thomas Palmeira Ferraz , Marcely Zanon Boito , Caroline Brun , Vassilina Nikoulina

Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…

Computation and Language · Computer Science 2023-06-22 Ziji Zhang , Zhehui Wang , Rajesh Kamma , Sharanya Eswaran , Narayanan Sadagopan

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…

Computation and Language · Computer Science 2024-05-13 Dena Mujtaba , Nihar R. Mahapatra , Megan Arney , J. Scott Yaruss , Hope Gerlach-Houck , Caryn Herring , Jia Bin

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

Computation and Language · Computer Science 2024-05-03 Thomas Palmeira Ferraz

Automatic Speech Recognition (ASR) systems, such as Whisper, achieve high transcription accuracy but struggle with named entities and numerical data, especially when proper formatting is required. These issues increase word error rate (WER)…

Computation and Language · Computer Science 2025-07-01 Duygu Altinok

Non-autoregressive (NAR) models have achieved a large inference computation reduction and comparable results with autoregressive (AR) models on various sequence to sequence tasks. However, there has been limited research aiming to explore…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Pengcheng Guo , Xuankai Chang , Shinji Watanabe , Lei Xie

This paper proposes AS-ASR, a lightweight aphasia-specific speech recognition framework based on Whisper-tiny, tailored for low-resource deployment on edge devices. Our approach introduces a hybrid training strategy that systematically…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-03 Chen Bao , Chuanbing Huo , Qinyu Chen , Chang Gao

Code-switching (CS) automatic speech recognition (ASR) faces challenges due to the language confusion resulting from accents, auditory similarity, and seamless language switches. Adaptation on the pre-trained multi-lingual model has shown…

Computation and Language · Computer Science 2025-01-07 Jiahui Zhao , Hao Shi , Chenrui Cui , Tianrui Wang , Hexin Liu , Zhaoheng Ni , Lingxuan Ye , Longbiao Wang

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Computation and Language · Computer Science 2025-08-20 Duygu Altinok

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

Computation and Language · Computer Science 2025-11-13 Jingyu Liu , Xin Dong , Zhifan Ye , Rishabh Mehta , Yonggan Fu , Vartika Singh , Jan Kautz , Ce Zhang , Pavlo Molchanov

Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on using the diffusion-based large language model LLaDA for…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-02 Mengqi Wang , Zhan Liu , Zengrui Jin , Guangzhi Sun , Chao Zhang , Philip C. Woodland

Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility…

Sound · Computer Science 2025-06-03 Xueyuan Chen , Dongchao Yang , Wenxuan Wu , Minglin Wu , Jing Xu , Xixin Wu , Zhiyong Wu , Helen Meng