English
Related papers

Related papers: Improving the Training Recipe for a Robust Conform…

200 papers

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition…

Sound · Computer Science 2022-07-18 Bowen Shi , Wei-Ning Hsu , Abdelrahman Mohamed

Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional way of LM training treats all the words in corpora equally, resulting in…

Computation and Language · Computer Science 2023-10-18 Yingyi Ma , Zhe Liu , Ozlem Kalinli

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we study how to reduce…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-09 Maxime Burchi , Valentin Vielzeuf

In this paper, we initiate the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module. We start from the standard ASV framework of…

Sound · Computer Science 2022-04-27 Xuechen Liu , Md Sahidullah , Tomi Kinnunen

In recent years, automatic speech recognition (ASR) models greatly improved transcription performance both in clean, low noise, acoustic conditions and in reverberant environments. However, all these systems rely on the availability of…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-18 Francesco Nespoli , Daniel Barreda , Patrick A. Naylor

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Claudio Zito , Fabio Tesser , Mauro Nicolao , Piero Cosi

Recently, fine-tuning large pre-trained Transformer models using downstream datasets has received a rising interest. Despite their success, it is still challenging to disentangle the benefits of large-scale datasets and Transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-19 Junyi Peng , Oldřich Plchot , Themos Stafylakis , Ladislav Mošner , Lukáš Burget , Jan Černocký

The developments in transformer encoder-decoder architectures have led to significant breakthroughs in machine translation, Automatic Speech Recognition (ASR), and instruction-based chat machines, among other applications. The pre-trained…

Computation and Language · Computer Science 2025-06-30 Kartheek Kumar Reddy Nareddy , Sarah Ternus , Julia Niebling

Dysarthric speech recognition (DSR) enhances the accessibility of smart devices for dysarthric speakers with limited mobility. Previously, DSR research was constrained by the fact that existing datasets typically consisted of isolated…

Sound · Computer Science 2025-07-01 Shiyao Wang , Jiaming Zhou , Shiwan Zhao , Yong Qin

Continued improvements in machine learning techniques offer exciting new opportunities through the use of larger models and larger training datasets. However, there is a growing need to offer these new capabilities on-board low-powered…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-16 Steven M. Hernandez , Ding Zhao , Shaojin Ding , Antoine Bruguier , Rohit Prabhavalkar , Tara N. Sainath , Yanzhang He , Ian McGraw

Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-29 Zhongzhi Yu , Yang Zhang , Kaizhi Qian , Yonggan Fu , Yingyan Lin

Automatic Speech Recognition systems have made significant progress with large-scale pre-trained models. However, most current systems focus solely on transcribing the speech without identifying speaker roles, a function that is critical…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-13 Anfeng Xu , Tiantian Feng , Shrikanth Narayanan

Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize "who spoke what" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-21 Naoyuki Kanda , Xiong Xiao , Jian Wu , Tianyan Zhou , Yashesh Gaur , Xiaofei Wang , Zhong Meng , Zhuo Chen , Takuya Yoshioka

Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited…

Computer Vision and Pattern Recognition · Computer Science 2023-03-30 Paul Hongsuck Seo , Arsha Nagrani , Cordelia Schmid

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data…

Computation and Language · Computer Science 2024-11-05 Chenpeng Du , Hao Li , Yizhou Lu , Lan Wang , Yanmin Qian

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

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

We present state-of-the-art automatic speech recognition (ASR) systems employing a standard hybrid DNN/HMM architecture compared to an attention-based encoder-decoder design for the LibriSpeech task. Detailed descriptions of the system…

Computation and Language · Computer Science 2019-10-02 Christoph Lüscher , Eugen Beck , Kazuki Irie , Markus Kitza , Wilfried Michel , Albert Zeyer , Ralf Schlüter , Hermann Ney

SpecAugment is a very effective data augmentation method for both HMM and E2E-based automatic speech recognition (ASR) systems. Especially, it also works in low-resource scenarios. However, SpecAugment masks the spectrum of time or the…

Sound · Computer Science 2022-10-18 Rui Li , Guodong Ma , Dexin Zhao , Ranran Zeng , Xiaoyu Li , Hao Huang

Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute --…

Computation and Language · Computer Science 2022-02-14 Chak-Fai Li , Francis Keith , William Hartmann , Matthew Snover