English
Related papers

Related papers: Curriculum Pre-training for End-to-End Speech Tran…

200 papers

Recently, the recurrent neural network transducer (RNN-T) architecture has become an emerging trend in end-to-end automatic speech recognition research due to its advantages of being capable for online streaming speech recognition. However,…

Computation and Language · Computer Science 2020-05-05 Hu Hu , Rui Zhao , Jinyu Li , Liang Lu , Yifan Gong

Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts. Several recent works have…

Computation and Language · Computer Science 2019-04-16 Matthias Sperber , Graham Neubig , Jan Niehues , Alex Waibel

Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-07 Keyu An , Zhijian Ou

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-04 Thai-Son Nguyen , Sebastian Stueker , Alex Waibel

Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this…

Computation and Language · Computer Science 2022-04-12 Orion Weller , Matthias Sperber , Telmo Pires , Hendra Setiawan , Christian Gollan , Dominic Telaar , Matthias Paulik

The encoder-decoder models for unsupervised sentence representation learning tend to discard the decoder after being trained on a large unlabelled corpus, since only the encoder is needed to map the input sentence into a vector…

Neural and Evolutionary Computing · Computer Science 2019-06-03 Shuai Tang , Virginia R. de Sa

End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even…

Computation and Language · Computer Science 2021-09-03 Peter Polák , Ondřej Bojar

We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art…

Computation and Language · Computer Science 2023-07-17 He Huang , Jagadeesh Balam , Boris Ginsburg

A key desiderata for inclusive and accessible speech recognition technology is ensuring its robust performance to children's speech. Notably, this includes the rapidly advancing neural network based end-to-end speech recognition systems.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-22 Prashanth Gurunath Shivakumar , Shrikanth Narayanan

Pre-training and representation learning have been playing an increasingly important role in modern speech processing. Nevertheless, different applications have been relying on different foundation models, since predominant pre-training…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-04 Alexander H. Liu , Sang-gil Lee , Chao-Han Huck Yang , Yuan Gong , Yu-Chiang Frank Wang , James R. Glass , Rafael Valle , Bryan Catanzaro

Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…

Computation and Language · Computer Science 2018-02-26 Dmitriy Serdyuk , Yongqiang Wang , Christian Fuegen , Anuj Kumar , Baiyang Liu , Yoshua Bengio

End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-15 Archiki Prasad , Preethi Jyothi , Rajbabu Velmurugan

There are individual differences in expressive behaviors driven by cultural norms and personality. This between-person variation can result in reduced emotion recognition performance. Therefore, personalization is an important step in…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-06 Minh Tran , Yufeng Yin , Mohammad Soleymani

A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the…

Computation and Language · Computer Science 2019-08-02 Muthuraman Chidambaram , Yinfei Yang , Daniel Cer , Steve Yuan , Yun-Hsuan Sung , Brian Strope , Ray Kurzweil

Speech translation (ST) is the task of directly translating acoustic speech signals in a source language into text in a foreign language. ST task has been addressed, for a long time, using a pipeline approach with two modules : first an…

Computation and Language · Computer Science 2022-12-13 Fethi Bougares , Salim Jouili

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Xueli Jia , Jianzong Wang , Zhiyong Zhang , Ning Cheng , Jing Xiao

Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…

Computation and Language · Computer Science 2019-01-08 Yunsu Kim , Jiahui Geng , Hermann Ney

When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder. An important limitation…

Signal Processing · Electrical Eng. & Systems 2021-10-22 Sangwoo Park , Osvaldo Simeone , Joonhyuk Kang

This paper presents a novel streaming end-to-end target-speaker speech recognition that addresses two critical limitations in systems: the handling of noisy enrollment utterances and specific enrollment phrase requirements. This paper…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-28 Mohsen Ghane , Mohammad Sadegh Safari

In this paper, we explore a method for training speech-to-speech translation tasks without any transcription or linguistic supervision. Our proposed method consists of two steps: First, we train and generate discrete representation with…

Computation and Language · Computer Science 2019-10-08 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura