English
Related papers

Related papers: On Architectures and Training for Raw Waveform Fea…

200 papers

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Computation and Language · Computer Science 2017-11-07 Yu-An Chung , James Glass

In this paper, we conduct a cross-dataset study on parametric and non-parametric raw-waveform based speaker embeddings through speaker verification experiments. In general, we observe a more significant performance degradation of these…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-13 Ge Zhu , Frank Cwitkowitz , Zhiyao Duan

This work introduces the Cleanformer, a streaming multichannel neural based enhancement frontend for automatic speech recognition (ASR). This model has a conformer-based architecture which takes as inputs a single channel each of raw and…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-05 Joseph Caroselli , Arun Narayanan , Nathan Howard , Tom O'Malley

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data available; most audio-visual datasets are collected in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-11-05 Ju-Chieh Chou , Chung-Ming Chien , Karen Livescu

Speech recognition from raw waveform involves learning the spectral decomposition of the signal in the first layer of the neural acoustic model using a convolution layer. In this work, we propose a raw waveform convolutional filter learning…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-22 Purvi Agrawal , Sriram Ganapathy

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-09 Qiushi Zhu , Jie Zhang , Yu Gu , Yuchen Hu , Lirong Dai

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-28 Qiu-Shi Zhu , Long Zhou , Jie Zhang , Shu-Jie Liu , Yu-Chen Hu , Li-Rong Dai

We present a method for transferring pre-trained self-supervised (SSL) speech representations to multiple languages. There is an abundance of unannotated speech, so creating self-supervised representations from raw audio and fine-tuning on…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-08 Samuel Kessler , Bethan Thomas , Salah Karout

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-16 Keqi Deng , Songjun Cao , Long Ma

Employing pre-trained language models (LM) to extract contextualized word representations has achieved state-of-the-art performance on various NLP tasks. However, applying this technique to noisy transcripts generated by automatic speech…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

There are several domains that own corresponding widely used feature extractors, such as ResNet, BERT, and GPT-x. These models are usually pre-trained on large amounts of unlabeled data by self-supervision and can be effectively applied to…

Computation and Language · Computer Science 2021-01-19 Cheng Yi , Jianzhong Wang , Ning Cheng , Shiyu Zhou , Bo Xu

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…

Cryptography and Security · Computer Science 2021-03-08 Shehzeen Hussain , Paarth Neekhara , Shlomo Dubnov , Julian McAuley , Farinaz Koushanfar

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Sound · Computer Science 2022-03-29 Xichen Pan , Peiyu Chen , Yichen Gong , Helong Zhou , Xinbing Wang , Zhouhan Lin

Unsupervised representation learning has recently helped automatic speech recognition (ASR) to tackle tasks with limited labeled data. Following this, hardware limitations and applications give rise to the question how to take advantage of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-21 Peter Vieting , Christoph Lüscher , Julian Dierkes , Ralf Schlüter , Hermann Ney

Automatic Speech Recognition (ASR) systems often struggle to accurately process children's speech due to its distinct and highly variable acoustic and linguistic characteristics. While recent advancements in self-supervised learning (SSL)…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-01 Abhijit Sinha , Hemant Kumar Kathania , Sudarsana Reddy Kadiri , Shrikanth Narayanan

This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions. These systems consists of a number of diverse subsystems based on using deep neural…

Recent advancements in neural audio codecs have not only enabled superior audio compression but also enhanced speech synthesis techniques. Researchers are now exploring their potential as universal acoustic feature extractors for a broader…

Audio and Speech Processing · Electrical Eng. & Systems 2025-11-21 Wei-Cheng Tseng , David Harwath

We focus on automatic feature extraction for raw audio heartbeat sounds, aimed at anomaly detection applications in healthcare. We learn features with the help of an autoencoder composed by a 1D non-causal convolutional encoder and a…

Sound · Computer Science 2021-02-25 Robert-George Colt , Csongor-Huba Várady , Riccardo Volpi , Luigi Malagò

Deep neural networks can learn complex and abstract representations, that are progressively obtained by combining simpler ones. A recent trend in speech and speaker recognition consists in discovering these representations starting from raw…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-26 Mirco Ravanelli , Yoshua Bengio