English
Related papers

Related papers: Improving Streaming Transformer Based ASR Under a …

200 papers

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Sound · Computer Science 2020-07-02 Niko Moritz , Takaaki Hori , Jonathan Le Roux

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-02 Daniel S. Park , Yu Zhang , Ye Jia , Wei Han , Chung-Cheng Chiu , Bo Li , Yonghui Wu , Quoc V. Le

Dual learning is a paradigm for semi-supervised machine learning that seeks to leverage unsupervised data by solving two opposite tasks at once. In this scheme, each model is used to generate pseudo-labels for unlabeled examples that are…

Computation and Language · Computer Science 2023-01-12 Cal Peyser , Ronny Huang , Tara Sainath , Rohit Prabhavalkar , Michael Picheny , Kyunghyun Cho

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Computation and Language · Computer Science 2021-01-28 Jiahui Yu , Wei Han , Anmol Gulati , Chung-Cheng Chiu , Bo Li , Tara N. Sainath , Yonghui Wu , Ruoming Pang

We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions. We perform experiments on the standard LibriSpeech…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure…

Computation and Language · Computer Science 2023-06-28 Haitao Tang , Yu Fu , Lei Sun , Jiabin Xue , Dan Liu , Yongchao Li , Zhiqiang Ma , Minghui Wu , Jia Pan , Genshun Wan , Ming'en Zhao

High quality transcription data is crucial for training automatic speech recognition (ASR) systems. However, the existing industry-level data collection pipelines are expensive to researchers, while the quality of crowdsourced transcription…

Computation and Language · Computer Science 2023-09-27 Jian Gao , Hanbo Sun , Cheng Cao , Zheng Du

Recent advances in machine learning have demonstrated that multi-modal pre-training can improve automatic speech recognition (ASR) performance compared to randomly initialized models, even when models are fine-tuned on uni-modal tasks.…

Computation and Language · Computer Science 2024-04-01 Yash Jain , David Chan , Pranav Dheram , Aparna Khare , Olabanji Shonibare , Venkatesh Ravichandran , Shalini Ghosh

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-22 Yu Zhang , James Qin , Daniel S. Park , Wei Han , Chung-Cheng Chiu , Ruoming Pang , Quoc V. Le , Yonghui Wu

Unpaired text and audio injection have emerged as dominant methods for improving ASR performance in the absence of a large labeled corpus. However, little guidance exists on deploying these methods to improve production ASR systems that are…

Computation and Language · Computer Science 2023-04-24 Cal Peyser , Michael Picheny , Kyunghyun Cho , Rohit Prabhavalkar , Ronny Huang , Tara Sainath

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Abdul Hannan , Alessio Brutti , Shah Nawaz , Mubashir Noman

Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy…

Computation and Language · Computer Science 2022-11-17 Suyoun Kim , Ke Li , Lucas Kabela , Rongqing Huang , Jiedan Zhu , Ozlem Kalinli , Duc Le

This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We particularly focus on the scene context provided by the visual information, to ground the ASR. We extract…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-01 Georgios Paraskevopoulos , Srinivas Parthasarathy , Aparna Khare , Shiva Sundaram

Speech separation has been successfully applied as a frontend processing module of conversation transcription systems thanks to its ability to handle overlapped speech and its flexibility to combine with downstream tasks such as automatic…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-06 Jian Wu , Zhuo Chen , Sanyuan Chen , Yu Wu , Takuya Yoshioka , Naoyuki Kanda , Shujie Liu , Jinyu Li

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming. Factors such as the quality and consistency of the…

Machine Learning · Computer Science 2022-07-05 Dongseong Hwang , Khe Chai Sim , Zhouyuan Huo , Trevor Strohman

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

Computation and Language · Computer Science 2019-10-24 Oleksii Hrinchuk , Mariya Popova , Boris Ginsburg

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Computation and Language · Computer Science 2022-02-08 Bethan Thomas , Samuel Kessler , Salah Karout

Self-supervised pretrained models exhibit competitive performance in automatic speech recognition on finetuning, even with limited in-domain supervised data. However, popular pretrained models are not suitable for streaming ASR because they…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-10 Shashi Kumar , Srikanth Madikeri , Juan Zuluaga-Gomez , Esaú Villatoro-Tello , Iuliia Thorbecke , Petr Motlicek , Manjunath K E , Aravind Ganapathiraju
‹ Prev 1 2 3 10 Next ›