中文
相关论文

相关论文: Investigation of Monaural Front-End Processing for…

200 篇论文

We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse…

音频与语音处理 · 电气工程与系统科学 2020-07-09 Vineel Pratap , Anuroop Sriram , Paden Tomasello , Awni Hannun , Vitaliy Liptchinsky , Gabriel Synnaeve , Ronan Collobert

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

音频与语音处理 · 电气工程与系统科学 2020-10-27 Jagadeesh Balam , Jocelyn Huang , Vitaly Lavrukhin , Slyne Deng , Somshubra Majumdar , Boris Ginsburg

Using neural network based acoustic frontends for improving robustness of streaming automatic speech recognition (ASR) systems is challenging because of the causality constraints and the resulting distortion that the frontend processing…

音频与语音处理 · 电气工程与系统科学 2022-04-27 Arun Narayanan , James Walker , Sankaran Panchapagesan , Nathan Howard , Yuma Koizumi

Jointly training a speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end has been investigated as a way to mitigate the influence of \emph{processing distortion} generated by single-channel SE on ASR. In this…

音频与语音处理 · 电气工程与系统科学 2023-11-21 Kazuma Iwamoto , Tsubasa Ochiai , Marc Delcroix , Rintaro Ikeshita , Hiroshi Sato , Shoko Araki , Shigeru Katagiri

In multi-channel speech enhancement and robust automatic speech recognition (ASR), beamforming can typically improve the signal-to-noise ratio (SNR) of the target speaker and produce reliable enhancement with little distortion to target…

音频与语音处理 · 电气工程与系统科学 2025-07-22 Zhong-Qiu Wang , Ruizhe Pang

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occurs with monolingual…

音频与语音处理 · 电气工程与系统科学 2020-06-02 Sanket Shah , Basil Abraham , Gurunath Reddy M , Sunayana Sitaram , Vikas Joshi

This paper summarizes several follow-up contributions for improving our submitted NWPU speaker-dependent system for CHiME-5 challenge, which aims to solve the problem of multi-channel, highly-overlapped conversational speech recognition in…

音频与语音处理 · 电气工程与系统科学 2019-04-09 Jian Wu , Yong Xu , Shi-Xiong Zhang , Lian-Wu Chen , Meng Yu , Lei Xie , Dong Yu

Speech enhancement methods are commonly believed to improve the performance of automatic speech recognition (ASR) in noisy environments. However, the effectiveness of these techniques cannot be taken for granted in the case of modern…

Multilingual pretraining for transfer learning significantly boosts the robustness of low-resource monolingual ASR models. This study systematically investigates three main aspects: (a) the impact of transfer learning on model performance…

计算与语言 · 计算机科学 2024-07-24 Laxmi Pandey , Ke Li , Jinxi Guo , Debjyoti Paul , Arthur Guo , Jay Mahadeokar , Xuedong Zhang

Recently, the end-to-end training approach for multi-channel ASR has shown its effectiveness, which usually consists of a beamforming front-end and a recognition back-end. However, the end-to-end training becomes more difficult due to the…

音频与语音处理 · 电气工程与系统科学 2022-10-11 Keyu An , Ji Xiao , Zhijian Ou

Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…

计算与语言 · 计算机科学 2019-02-21 Ozan Caglayan , Ramon Sanabria , Shruti Palaskar , Loïc Barrault , Florian Metze

This work presents our end-to-end (E2E) automatic speech recognition (ASR) model targetting at robust speech recognition, called Integraded speech Recognition with enhanced speech Input for Self-supervised learning representation (IRIS).…

声音 · 计算机科学 2022-04-04 Xuankai Chang , Takashi Maekaku , Yuya Fujita , Shinji Watanabe

With the advent of deep learning, research on noise-robust automatic speech recognition (ASR) has progressed rapidly. However, ASR performance in noisy conditions of single-channel systems remains unsatisfactory. Indeed, most single-channel…

音频与语音处理 · 电气工程与系统科学 2020-03-10 Keisuke Kinoshita , Tsubasa Ochiai , Marc Delcroix , Tomohiro Nakatani

Automatic speech recognition (ASR) in multichannel, multi-speaker scenarios remains challenging due to ambient noise, reverberation and overlapping speakers. In this paper, we propose a beamforming approach that processes specific angular…

声音 · 计算机科学 2025-09-15 Can Cui , Paul Magron , Mostafa Sadeghi , Emmanuel Vincent

This paper presents the contribution to the third 'CHiME' speech separation and recognition challenge including both front-end signal processing and back-end speech recognition. In the front-end, Multi-channel Wiener filter (MWF) is…

声音 · 计算机科学 2015-09-22 Xiaofei Wang , Chao Wu , Pengyuan Zhang , Ziteng Wang , Yong Liu , Xu Li , Qiang Fu , Yonghong Yan

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

音频与语音处理 · 电气工程与系统科学 2020-02-19 Ankur Gandhe , Ariya Rastrow

Automatic speech recognition (ASR) systems degrade significantly under noisy conditions. Recently, speech enhancement (SE) is introduced as front-end to reduce noise for ASR, but it also suppresses some important speech information, i.e.,…

音频与语音处理 · 电气工程与系统科学 2023-05-30 Yuchen Hu , Nana Hou , Chen Chen , Eng Siong Chng

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…

音频与语音处理 · 电气工程与系统科学 2025-09-15 Peter Vieting , Benedikt Hilmes , Ralf Schlüter , Hermann Ney

In this study, we investigate whether noise-augmented training can concurrently improve adversarial robustness in automatic speech recognition (ASR) systems. We conduct a comparative analysis of the adversarial robustness of four different…

音频与语音处理 · 电气工程与系统科学 2025-11-10 Karla Pizzi , Matías Pizarro , Asja Fischer

Neural front-ends are an appealing alternative to traditional, fixed feature extraction pipelines for automatic speech recognition (ASR) systems since they can be directly trained to fit the acoustic model. However, their performance often…

音频与语音处理 · 电气工程与系统科学 2025-10-01 Peter Vieting , Maximilian Kannen , Benedikt Hilmes , Ralf Schlüter , Hermann Ney