English
Related papers

Related papers: In-domain SSL pre-training and streaming ASR

200 papers

We present a simple approach to improve direct speech-to-text translation (ST) when the source language is low-resource: we pre-train the model on a high-resource automatic speech recognition (ASR) task, and then fine-tune its parameters…

Computation and Language · Computer Science 2019-03-01 Sameer Bansal , Herman Kamper , Karen Livescu , Adam Lopez , Sharon Goldwater

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

Large scale machine learning (ML) systems such as the Alexa automatic speech recognition (ASR) system continue to improve with increasing amounts of manually transcribed training data. Instead of scaling manual transcription to impractical…

Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL)…

Sound · Computer Science 2023-12-18 Avner May , Dmitriy Serdyuk , Ankit Parag Shah , Otavio Braga , Olivier Siohan

Utilizing air-traffic control (ATC) data for downstream natural-language processing tasks requires preprocessing steps. Key steps are the transcription of the data via automatic speech recognition (ASR) and speaker diarization, respectively…

Computation and Language · Computer Science 2024-06-21 Alexander Blatt , Aravind Krishnan , Dietrich Klakow

While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue. In this work, we propose a self-training method with an end-to-end system…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-31 Yang Chen , Weiran Wang , Chao Wang

Radio speech echo is a specific phenomenon in the air traffic control (ATC) domain, which degrades speech quality and further impacts automatic speech recognition (ASR) accuracy. In this work, a time-domain recognition-oriented speech…

Sound · Computer Science 2024-07-31 Xincheng Yu , Dongyue Guo , Jianwei Zhang , Yi Lin

Advancements in self-supervised pre-training (SSL) have significantly advanced the field of learning transferable time series representations, which can be very useful in enhancing the downstream task. Despite being effective, most existing…

Machine Learning · Computer Science 2024-11-06 Mingyue Cheng , Xiaoyu Tao , Qi Liu , Hao Zhang , Yiheng Chen , Defu Lian

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Computation and Language · Computer Science 2021-01-28 Jiahui Yu , Wei Han , Anmol Gulati , Chung-Cheng Chiu , Bo Li , Tara N. Sainath , Yonghui Wu , Ruoming Pang

Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a…

Computation and Language · Computer Science 2026-03-13 Youness Dkhissi , Valentin Vielzeuf , Elys Allesiardo , Anthony Larcher

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

Computation and Language · Computer Science 2022-05-03 Felix Wu , Kwangyoun Kim , Shinji Watanabe , Kyu Han , Ryan McDonald , Kilian Q. Weinberger , Yoav Artzi

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Sound · Computer Science 2020-07-02 Niko Moritz , Takaaki Hori , Jonathan Le Roux

Continued pre-training (CP) offers multiple advantages, like target domain adaptation and the potential to exploit the continuous stream of unlabeled data available online. However, continued pre-training on out-of-domain distributions…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-21 Ashish Seth , Sreyan Ghosh , S. Umesh , Dinesh Manocha

The training of automatic speech recognition (ASR) with little to no supervised data remains an open question. In this work, we demonstrate that streaming Transformer-Transducer (TT) models can be trained from scratch in consumer and…

Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…

Audio and Speech Processing · Electrical Eng. & Systems 2025-08-28 Carlos Carvalho , Alberto Abad

The use of synthetic speech as data augmentation is gaining increasing popularity in fields such as automatic speech recognition and speech classification tasks. Despite novel text-to-speech systems with voice cloning capabilities, that…

Sound · Computer Science 2024-09-20 Sebastião Quintas , Isabelle Ferrané , Thomas Pellegrini

Streaming automatic speech recognition (ASR) is very important for many real-world ASR applications. However, a notable challenge for streaming ASR systems lies in balancing operational performance against latency constraint. Recently, a…

Sound · Computer Science 2024-09-17 Wenbo Zhao , Ziwei Li , Chuan Yu , Zhijian Ou

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-15 Lixin Cao , Jun Wang , Ben Yang , Dan Su , Dong Yu

Thanks to the rise of self-supervised learning, automatic speech recognition (ASR) systems now achieve near-human performance on a wide variety of datasets. However, they still lack generalization capability and are not robust to domain…

Machine Learning · Computer Science 2023-03-15 Lucas Maison , Yannick Estève

Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available,…

Machine Learning · Computer Science 2023-03-21 Yongyi Su , Xun Xu , Tianrui Li , Kui Jia
‹ Prev 1 3 4 5 6 7 10 Next ›