English
Related papers

Related papers: End-to-End Speech Recognition and Disfluency Remov…

200 papers

Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU). Through the term end-to-end, one considers the use of a single model optimized to extract semantic information…

Computation and Language · Computer Science 2022-04-05 Salima Mdhaffar , Jarod Duret , Titouan Parcollet , Yannick Estève

Current de-facto dysfluency modeling methods utilize template matching algorithms which are not generalizable to out-of-domain real-world dysfluencies across languages, and are not scalable with increasing amounts of training data. To…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Computation and Language · Computer Science 2018-12-06 Zhehuai Chen , Mahaveer Jain , Yongqiang Wang , Michael L. Seltzer , Christian Fuegen

Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition. However, the causality and latency constraints of production systems put end-to-end…

Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level. The E2E systems implicitly model all conventional ASR components, such as the…

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer…

Computation and Language · Computer Science 2020-11-10 Chunxi Liu , Frank Zhang , Duc Le , Suyoun Kim , Yatharth Saraf , Geoffrey Zweig

Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Takafumi Moriya , Hiroshi Sato , Tsubasa Ochiai , Marc Delcroix , Takahiro Shinozaki

Non-autoregressive (NAR) models simultaneously generate multiple outputs in a sequence, which significantly reduces the inference speed at the cost of accuracy drop compared to autoregressive baselines. Showing great potential for real-time…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-12 Yosuke Higuchi , Nanxin Chen , Yuya Fujita , Hirofumi Inaguma , Tatsuya Komatsu , Jaesong Lee , Jumon Nozaki , Tianzi Wang , Shinji Watanabe

A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text. Such modeling suffers…

Computation and Language · Computer Science 2020-11-25 Parnia Bahar , Tobias Bieschke , Ralf Schlüter , Hermann Ney

Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-12 Muhammad Shakeel , Yui Sudo , Yifan Peng , Shinji Watanabe

Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract mel-filterbanks or cepstral coefficients. In this paper we…

Computation and Language · Computer Science 2019-04-10 Neil Zeghidour , Qiantong Xu , Vitaliy Liptchinsky , Nicolas Usunier , Gabriel Synnaeve , Ronan Collobert

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Computation and Language · Computer Science 2022-06-16 Alexander H. Liu , Wei-Ning Hsu , Michael Auli , Alexei Baevski

Sound event detection systems typically consist of two stages: extracting hand-crafted features from the raw audio waveform, and learning a mapping between these features and the target sound events using a classifier. Recently, the focus…

Sound · Computer Science 2018-05-11 Emre Çakır , Tuomas Virtanen

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to grammatical errors, disfluency, and other…

Computation and Language · Computer Science 2020-04-10 Junwei Liao , Sefik Emre Eskimez , Liyang Lu , Yu Shi , Ming Gong , Linjun Shou , Hong Qu , Michael Zeng

We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…

Computation and Language · Computer Science 2022-07-13 Aparna Khare , Eunjung Han , Yuguang Yang , Andreas Stolcke

Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…

Computation and Language · Computer Science 2023-06-22 Simon Berger , Peter Vieting , Christoph Boeddeker , Ralf Schlüter , Reinhold Haeb-Umbach

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

Sound · Computer Science 2022-02-18 Kun Wei , Yike Zhang , Sining Sun , Lei Xie , Long Ma

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent…

Computation and Language · Computer Science 2021-08-06 Yidi Jiang , Bidisha Sharma , Maulik Madhavi , Haizhou Li

TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact)…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-17 Jakob Poncelet , Hugo Van hamme

Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall performance but cannot reveal why models succeed or fail.…