English
Related papers

Related papers: Early Attentive Sparsification Accelerates Neural …

200 papers

Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or…

Sound · Computer Science 2023-07-12 Max Bain , Jaesung Huh , Tengda Han , Andrew Zisserman

Large transformer-based models have significant potential for speech transcription and translation. Their self-attention mechanisms and parallel processing enable them to capture complex patterns and dependencies in audio sequences.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-25 Yael Segal-Feldman , Aviv Shamsian , Aviv Navon , Gill Hetz , Joseph Keshet

Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming…

Computation and Language · Computer Science 2026-04-07 Tomer Krichli , Bhiksha Raj , Joseph Keshet

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-29 Sunghwan Ahn , Jinmo Han , Beom Jun Woo , Nam Soo Kim

Speech coding facilitates the transmission of speech over low-bandwidth networks with minimal distortion. Neural-network based speech codecs have recently demonstrated significant improvements in quality over traditional approaches. While…

Sound · Computer Science 2022-07-07 Ali Siahkoohi , Michael Chinen , Tom Denton , W. Bastiaan Kleijn , Jan Skoglund

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel

Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc. However, most of current approaches are computationally…

We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We…

Machine Learning · Computer Science 2024-08-30 Laurin Wagner , Bernhard Thallinger , Mario Zusag

Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we build on top of Whisper and create Whisper-Streaming, an…

Computation and Language · Computer Science 2023-09-22 Dominik Macháček , Raj Dabre , Ondřej Bojar

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-31 Desh Raj , Junteng Jia , Jay Mahadeokar , Chunyang Wu , Niko Moritz , Xiaohui Zhang , Ozlem Kalinli

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…

Computation and Language · Computer Science 2023-03-14 Stefan Braun , Erik McDermott , Roger Hsiao

In this paper, we focus on Whisper, a recent automatic speech recognition model trained with a massive 680k hour labeled speech corpus recorded in diverse conditions. We first show an interesting finding that while Whisper is very robust…

Sound · Computer Science 2023-10-10 Yuan Gong , Sameer Khurana , Leonid Karlinsky , James Glass

Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data. Attention-based biasing is a leading approach which…

As one of the most popular sequence-to-sequence modeling approaches for speech recognition, the RNN-Transducer has achieved evolving performance with more and more sophisticated neural network models of growing size and increasing training…

Computation and Language · Computer Science 2023-10-20 Wei Zhou , Wilfried Michel , Ralf Schlüter , Hermann Ney

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

End-to-end model, especially Recurrent Neural Network Transducer (RNN-T), has achieved great success in speech recognition. However, transducer requires a great memory footprint and computing time when processing a long decoding sequence.…

Sound · Computer Science 2023-07-18 Xiaohui Zhang , Mangui Liang , Zhengkun Tian , Jiangyan Yi , Jianhua Tao

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length…

Computation and Language · Computer Science 2023-10-19 Sara Papi , Marco Gaido , Matteo Negri , Marco Turchi

The Transformer architecture model, based on self-attention and multi-head attention, has achieved remarkable success in offline end-to-end Automatic Speech Recognition (ASR). However, self-attention and multi-head attention cannot be…

Computation and Language · Computer Science 2022-10-03 Chendong Zhao , Jianzong Wang , Wen qi Wei , Xiaoyang Qu , Haoqian Wang , Jing Xiao

Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks. Nonetheless, the capabilities of these encoders in low-resource settings are yet to be thoroughly…

Computation and Language · Computer Science 2023-05-30 Hao Yang , Jinming Zhao , Gholamreza Haffari , Ehsan Shareghi
‹ Prev 1 2 3 10 Next ›