English
Related papers

Related papers: Whale: Large-Scale multilingual ASR model with w2v…

200 papers

This paper presents our system for the MLC-SLM Challenge 2025, focusing on multilingual speech recognition and language modeling with large language models (LLMs). Our approach combines a fine-tuned Whisper-large-v3 encoder with efficient…

Computation and Language · Computer Science 2025-07-08 Tuan Nguyen , Long-Vu Hoang , Huy-Dat Tran

In automatic speech recognition, any factor that alters the acoustic properties of speech can pose a challenge to the system's performance. This paper presents a novel approach for automatic whispered speech recognition in the Irish dialect…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-05 Aref Farhadipour , Homa Asadi , Volker Dellwo

Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Mukuntha Narayanan Sundararaman , Ayush Kumar , Jithendra Vepa

Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only…

Computation and Language · Computer Science 2026-05-26 Akshat Pandey , Karun Kumar , Raphael Tang

There exist three approaches for multilingual and crosslingual automatic speech recognition (MCL-ASR) - supervised pretraining with phonetic or graphemic transcription, and self-supervised pretraining. We find that pretraining with phonetic…

Sound · Computer Science 2025-03-28 Saierdaer Yusuyin , Te Ma , Hao Huang , Wenbo Zhao , Zhijian Ou

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…

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 designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

Computation and Language · Computer Science 2022-02-11 Peter Sullivan , Toshiko Shibano , Muhammad Abdul-Mageed

Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous to use them in conventional ASR systems. While some…

Computation and Language · Computer Science 2024-04-22 Darshan Prabhu , Sai Ganesh Mirishkar , Pankaj Wasnik

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Georgios Paraskevopoulos , Srinivas Parthasarathy , Aparna Khare , Shiva Sundaram

This paper investigates the in-context learning abilities of the Whisper automatic speech recognition (ASR) models released by OpenAI. A novel speech-based in-context learning (SICL) approach is proposed for test-time adaptation, which can…

Audio and Speech Processing · Electrical Eng. & Systems 2024-03-21 Siyin Wang , Chao-Han Huck Yang , Ji Wu , Chao Zhang

Benefiting from massive and diverse data sources, speech foundation models exhibit strong generalization and knowledge transfer capabilities to a wide range of downstream tasks. However, a limitation arises from their exclusive handling of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-10 Pengcheng Guo , Xuankai Chang , Hang Lv , Shinji Watanabe , Lei Xie

This study evaluates the performance of three advanced speech encoder models, Wav2Vec 2.0, XLS-R, and Whisper, in speaker identification tasks. By fine-tuning these models and analyzing their layer-wise representations using SVCCA, k-means…

Sound · Computer Science 2025-09-30 Linus Stuhlmann , Michael Alexander Saxer

Wav2vec 2.0 (W2V2) has shown impressive performance in automatic speech recognition (ASR). However, the large model size and the non-streaming architecture make it hard to be used under low-resource or streaming scenarios. In this work, we…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-17 Yanzhe Fu , Yueteng Kang , Songjun Cao , Long Ma

Automatic Speech Recognition (ASR) systems have achieved remarkable performance on widely used benchmarks such as LibriSpeech and Fleurs. However, these benchmarks do not adequately reflect the complexities of real-world conversational…

Computation and Language · Computer Science 2024-09-19 Gaurav Maheshwari , Dmitry Ivanov , Théo Johannet , Kevin El Haddad

The Open Whisper-style Speech Model (OWSM) series was introduced to achieve full transparency in building advanced speech-to-text (S2T) foundation models. To this end, OWSM models are trained on 25 public speech datasets, which are…

Computation and Language · Computer Science 2024-06-14 Jinchuan Tian , Yifan Peng , William Chen , Kwanghee Choi , Karen Livescu , Shinji Watanabe

Large Language Models (LLMs) have demonstrated unparalleled effectiveness in various NLP tasks, and integrating LLMs with automatic speech recognition (ASR) is becoming a mainstream paradigm. Building upon this momentum, our research delves…

Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most…

Sound · Computer Science 2025-07-16 Atila Orhon , Arda Okan , Berkin Durmus , Zach Nagengast , Eduardo Pacheco

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

Computation and Language · Computer Science 2026-03-16 Wen Ding , Fan Qian

Speaker identification in multilingual settings presents unique challenges, particularly when conventional models are predominantly trained on English data. In this paper, we propose WSI (Whisper Speaker Identification), a framework that…

Sound · Computer Science 2025-03-14 Jakaria Islam Emon , Md Abu Salek , Kazi Tamanna Alam