English
Related papers

Related papers: Contextualized End-to-End Speech Recognition with …

200 papers

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

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Shuubham Ojha , Felix Gervits , Carol Espy-Wilson

Despite improvements to the generalization performance of automated speech recognition (ASR) models, specializing ASR models for downstream tasks remains a challenging task, primarily due to reduced data availability (necessitating…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-10 David M. Chan , Shalini Ghosh , Ariya Rastrow , Björn Hoffmeister

End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that…

Computation and Language · Computer Science 2023-06-06 Guangzhi Sun , Xianrui Zheng , Chao Zhang , Philip C. Woodland

This paper presents an experimental study on deep speaker embedding with an attention mechanism that has been found to be a powerful representation learning technique in speaker recognition. In this framework, an attention model works as a…

Sound · Computer Science 2018-09-26 Qiongqiong Wang , Koji Okabe , Kong Aik Lee , Hitoshi Yamamoto , Takafumi Koshinaka

Automatic speech recognition (ASR) is widely used in consumer electronics. ASR greatly improves the utility and accessibility of technology, but usually the output is only word sequences without punctuation. This can result in ambiguity in…

Computation and Language · Computer Science 2021-02-23 Andrew Silva , Barry-John Theobald , Nicholas Apostoloff

Recently, there has been an increasing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. One approach is the attention-based encoder-decoder framework that learns a mapping…

Computation and Language · Computer Science 2017-02-02 Suyoun Kim , Takaaki Hori , Shinji Watanabe

Term frequency is a common method for identifying the importance of a term in a query or document. But it is a weak signal, especially when the frequency distribution is flat, such as in long queries or short documents where the text is of…

Information Retrieval · Computer Science 2019-11-28 Zhuyun Dai , Jamie Callan

Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-11 Srikanth Raj Chetupalli , Sriram Ganapathy

This paper presents an extension to train end-to-end Context-Aware Transformer Transducer ( CATT ) models by using a simple, yet efficient method of mining hard negative phrases from the latent space of the context encoder. During training,…

Computation and Language · Computer Science 2023-08-17 Maurits Bleeker , Pawel Swietojanski , Stefan Braun , Xiaodan Zhuang

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

Computation and Language · Computer Science 2024-01-12 Jiaxin Guo , Minghan Wang , Xiaosong Qiao , Daimeng Wei , Hengchao Shang , Zongyao Li , Zhengzhe Yu , Yinglu Li , Chang Su , Min Zhang , Shimin Tao , Hao Yang

At present, the deep end-to-end method based on supervised learning is used in entity recognition and dependency analysis. There are two problems in this method: firstly, background knowledge cannot be introduced; secondly, multi…

Computation and Language · Computer Science 2020-07-09 Zheng Li , Gang Tu , Guang Liu , Zhi-Qiang Zhan , Yi-Jian Liu

Contextualized ASR models have been demonstrated to effectively improve the recognition accuracy of uncommon phrases when a predefined phrase list is available. However, these models often struggle with bilingual settings, which are…

Computation and Language · Computer Science 2024-08-21 Xucheng Wan , Naijun Zheng , Kai Liu , Huan Zhou

Neural network based approaches for sentence relation modeling automatically generate hidden matching features from raw sentence pairs. However, the quality of matching feature representation may not be satisfied due to complex semantic…

Computation and Language · Computer Science 2016-04-01 Peng Li , Heng Huang

Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in…

Sound · Computer Science 2023-04-14 Shun Lei , Yixuan Zhou , Liyang Chen , Zhiyong Wu , Shiyin Kang , Helen Meng

Automatic Speech Recognition (ASR) technology has made significant progress in recent years, providing accurate transcription across various domains. However, some challenges remain, especially in noisy environments and specialized jargon.…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-06 Aviv Shamsian , Aviv Navon , Neta Glazer , Gill Hetz , Joseph Keshet

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

Computation and Language · Computer Science 2022-07-04 Vishal Sunder , Eric Fosler-Lussier , Samuel Thomas , Hong-Kwang J. Kuo , Brian Kingsbury

Contextual knowledge is essential for reducing speech recognition errors on high-valued long-tail words. This paper proposes a novel tree-constrained pointer generator (TCPGen) component that enables end-to-end ASR models to bias towards a…

Computation and Language · Computer Science 2024-10-28 Guangzhi Sun , Chao Zhang , Philip C Woodland

While end-to-end models have shown great success on the Automatic Speech Recognition task, performance degrades severely when target sentences are long-form. The previous proposed methods, (partial) overlapping inference are shown to be…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-23 Jinhan Wang , Xiaosu Tong , Jinxi Guo , Di He , Roland Maas

This paper advances phrase break prediction (also known as phrasing) in multi-speaker text-to-speech (TTS) systems. We integrate speaker-specific features by leveraging speaker embeddings to enhance the performance of the phrasing model. We…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-03 Dong Yang , Yuki Saito , Takaaki Saeki , Tomoki Koriyama , Wataru Nakata , Detai Xin , Hiroshi Saruwatari