English
Related papers

Related papers: Improving Large-scale Deep Biasing with Phoneme Fe…

200 papers

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Computation and Language · Computer Science 2021-02-12 Yun Tang , Juan Pino , Changhan Wang , Xutai Ma , Dmitriy Genzel

We explore options to use Transformer networks in neural transducer for end-to-end speech recognition. Transformer networks use self-attention for sequence modeling and comes with advantages in parallel computation and capturing contexts.…

Audio and Speech Processing · Electrical Eng. & Systems 2019-10-30 Ching-Feng Yeh , Jay Mahadeokar , Kaustubh Kalgaonkar , Yongqiang Wang , Duc Le , Mahaveer Jain , Kjell Schubert , Christian Fuegen , Michael L. Seltzer

Adapting pre-trained text Large Language Models (LLMs) into Speech Language Models (Speech LMs) via continual pretraining on speech data is promising, but often degrades the original text capabilities. We propose Multimodal Depth Upscaling,…

Computation and Language · Computer Science 2026-04-02 Kazuki Yano , Jun Suzuki , Shinji Watanabe

This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-05 Shuo Liu , Leda Sarı , Chunyang Wu , Gil Keren , Yuan Shangguan , Jay Mahadeokar , Ozlem Kalinli

Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent…

Computation and Language · Computer Science 2025-09-03 Changsong Liu , Yizhou Peng , Eng Siong Chng

End-to-end (E2E) approach is gradually replacing hybrid models for automatic speech recognition (ASR) tasks. However, the optimization of E2E models lacks an intuitive method for handling decoding shifts, especially in scenarios with a…

Computation and Language · Computer Science 2024-03-04 Heyang Liu , Yu Wang , Yanfeng Wang

Large Audio Language Models (LALMs) have emerged as powerful tools for speech-related tasks but remain underexplored for fine-tuning, especially with limited speech data. To bridge this gap, we systematically examine how different…

Sound · Computer Science 2026-01-22 Youngwon Choi , Jaeyoon Jung , Hyeonyu Kim , Huu-Kim Nguyen , Hwayeon Kim

Recently Deep Transformer models have proven to be particularly powerful in language modeling tasks for ASR. Their high complexity, however, makes them very difficult to apply in the first (single) pass of an online system. Recent studies…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Balázs Tarján , György Szaszák , Tibor Fegyó , Péter Mihajlik

The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode, where it generates partial hypotheses before the complete…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-21 Rogier van Dalen

End-to-end automatic speech recognition (E2E ASR) systems have significantly improved speech recognition through training on extensive datasets. Despite these advancements, they still struggle to accurately recognize domain specific words,…

Computation and Language · Computer Science 2024-07-26 Jiwon Suh , Injae Na , Woohwan Jung

Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of…

Computation and Language · Computer Science 2024-07-18 Minh Nguyen , Franck Dernoncourt , Seunghyun Yoon , Hanieh Deilamsalehy , Hao Tan , Ryan Rossi , Quan Hung Tran , Trung Bui , Thien Huu Nguyen

Self-supervised learning of speech representations has achieved impressive results in improving automatic speech recognition (ASR). In this paper, we show that data selection is important for self-supervised learning. We propose a simple…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-06 Zhiyun Lu , Yongqiang Wang , Yu Zhang , Wei Han , Zhehuai Chen , Parisa Haghani

Automatic Speech Recognition (ASR) has witnessed a profound research interest. Recent breakthroughs have given ASR systems different prospects such as faithfully transcribing spoken language, which is a pivotal advancement in building…

Computation and Language · Computer Science 2024-03-05 Ankitha Sudarshan , Vinay Samuel , Parth Patwa , Ibtihel Amara , Aman Chadha

Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…

Computation and Language · Computer Science 2017-03-24 Mirco Ravanelli , Philemon Brakel , Maurizio Omologo , Yoshua Bengio

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

Computation and Language · Computer Science 2017-06-13 Xiaohui Zhang , Vimal Manohar , Daniel Povey , Sanjeev Khudanpur

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Computation and Language · Computer Science 2020-10-28 Suyoun Kim , Yuan Shangguan , Jay Mahadeokar , Antoine Bruguier , Christian Fuegen , Michael L. Seltzer , Duc Le

Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer…

Sound · Computer Science 2022-11-18 Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen , Yanmin Qian

Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that is similar to that on which it was trained. As such, underrepresented varieties including regional dialects, minority-speakers, and low-resource…

Computation and Language · Computer Science 2023-05-15 Emma O'Neill , Julie Carson-Berndsen

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-24 Yangui Fang , Jing Peng , Xu Li , Yu Xi , Chengwei Zhang , Guohui Zhong , Kai Yu
‹ Prev 1 4 5 6 7 8 10 Next ›