English
Related papers

Related papers: Exploring Architectures, Data and Units For Stream…

200 papers

We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-09 Minchan Kim , Myeonghun Jeong , Byoung Jin Choi , Dongjune Lee , Nam Soo Kim

Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the…

Computation and Language · Computer Science 2018-05-28 Wen Zhang , Jiawei Hu , Yang Feng , Qun Liu

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-18 Xi Wang , Huaiping Ming , Lei He , Frank K. Soong

This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then,…

Computation and Language · Computer Science 2018-07-31 Tomoki Hayashi , Shinji Watanabe , Tomoki Toda , Kazuya Takeda

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen

Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Thai-Son Nguyen , Ngoc-Quan Pham , Sebastian Stueker , Alex Waibel

We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-01 Yongqiang Wang , Zhehuai Chen , Chengjian Zheng , Yu Zhang , Wei Han , Parisa Haghani

Stream fusion, also known as system combination, is a common technique in automatic speech recognition for traditional hybrid hidden Markov model approaches, yet mostly unexplored for modern deep neural network end-to-end model…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-15 Timo Lohrenz , Zhengyang Li , Tim Fingscheidt

This paper proposes a novel approach for speech signal prediction based on a recurrent neural network (RNN). Unlike existing RNN-based predictors, which operate on parametric features and are trained offline on a large collection of such…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-17 Reza Lotfidereshgi , Philippe Gournay

RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-30 Dario Albesano , Jesús Andrés-Ferrer , Nicola Ferri , Puming Zhan

In this paper, we propose two novel approaches, which integrate long-content information into the factorized neural transducer (FNT) based architecture in both non-streaming (referred to as LongFNT ) and streaming (referred to as SLongFNT )…

Sound · Computer Science 2024-03-21 Xun Gong , Yu Wu , Jinyu Li , Shujie Liu , Rui Zhao , Xie Chen , Yanmin Qian

Confidence estimate is an often requested feature in applications such as medical transcription where errors can impact patient care and the confidence estimate could be used to alert medical professionals to verify potential errors in…

Computation and Language · Computer Science 2021-10-29 Mingqiu Wang , Hagen Soltau , Laurent El Shafey , Izhak Shafran

Compensation for channel mismatch and noise interference is essential for robust automatic speech recognition. Enhanced speech has been introduced into the multi-condition training of acoustic models to improve their generalization ability.…

Sound · Computer Science 2022-11-24 Hung-Shin Lee , Pin-Yuan Chen , Yao-Fei Cheng , Yu Tsao , Hsin-Min Wang

We present a novel end-to-end neural model to extract entities and relations between them. Our recurrent neural network based model captures both word sequence and dependency tree substructure information by stacking bidirectional…

Computation and Language · Computer Science 2016-06-09 Makoto Miwa , Mohit Bansal

Long short-term memory recurrent neural networks (LSTM-RNNs) are considered state-of-the art in many speech processing tasks. The recurrence in the network, in principle, allows any input to be remembered for an indefinite time, a feature…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-02 Jeroen Zegers , Hugo Van hamme

End-to-end Spoken Language Understanding (E2E SLU) has attracted increasing interest due to its advantages of joint optimization and low latency when compared to traditionally cascaded pipelines. Existing E2E SLU models usually follow a…

Computation and Language · Computer Science 2022-04-04 Xuandi Fu , Feng-Ju Chang , Martin Radfar , Kai Wei , Jing Liu , Grant P. Strimel , Kanthashree Mysore Sathyendra

Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent…

Computation and Language · Computer Science 2016-04-25 Ke Tran , Arianna Bisazza , Christof Monz

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Computation and Language · Computer Science 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

Machine Learning · Computer Science 2015-10-20 Zachary C. Lipton , John Berkowitz , Charles Elkan

Training speech recognition systems on noisy transcripts is a significant challenge in industrial pipelines, where datasets are enormous and ensuring accurate transcription for every instance is difficult. In this work, we introduce novel…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-10 Vladimir Bataev